initial app test

configs/cfg_test.yml

@@ -1,28 +0,0 @@
-EXP_NAME: 'damon_hrnet_testing'
-PROJECT_NAME: 'DECO_DAMON_Testing'
-OUTPUT_DIR: 'deco_results'
-CONDOR_DIR: ''
-DATASET:
-  BATCH_SIZE: 16
-  NUM_WORKERS: 4
-  NORMALIZE_IMAGES: [True]
-OPTIMIZER:
-  TYPE: 'adam'
-  LR: [5e-5]
-  NUM_UPDATE_LR: 3
-TRAINING:
-  ENCODER: 'hrnet'
-  CONTEXT: [True]
-  NUM_EPOCHS: 1
-  NUM_EARLY_STOP: 10
-  SUMMARY_STEPS: 5
-  CHECKPOINT_EPOCHS: 5
-  DATASETS: ['damon']
-  DATASET_MIX_PDF: ['1.']
-  DATASET_ROOT_PATH: ''
-  BEST_MODEL_PATH: './checkpoints/Release_Checkpoint/deco_best.pth'
-  PAL_LOSS_WEIGHTS: 0.0
-VALIDATION:
-  SUMMARY_STEPS: 1000
-  DATASETS: ['damon']
-  MAIN_DATASET: 'damon'

configs/cfg_train.yml

@@ -1,29 +0,0 @@
-EXP_NAME: 'demo_train'
-PROJECT_NAME: 'DECO_demo_training'
-OUTPUT_DIR: 'deco_results'
-CONDOR_DIR: ''
-DATASET:
-  BATCH_SIZE: 4
-  NUM_WORKERS: 8
-  NORMALIZE_IMAGES: [True]
-OPTIMIZER:
-  TYPE: 'adam'
-  LR: [1e-5]
-  NUM_UPDATE_LR: 3
-TRAINING:
-  ENCODER: 'hrnet'
-  CONTEXT: [True]
-  NUM_EPOCHS: 100
-  NUM_EARLY_STOP: 10
-  SUMMARY_STEPS: 5
-  CHECKPOINT_EPOCHS: 5
-  DATASETS: ['damon', 'rich', 'prox']
-  DATASET_MIX_PDF: ['0.4', '0.3', '0.3'] # should sum to 1.0 unless you want to weight by dataset size
-  DATASET_ROOT_PATH: ''
-  BEST_MODEL_PATH: './checkpoints/Other_Checkpoints/demo_train.pth'
-  LOSS_WEIGHTS: 1.
-  PAL_LOSS_WEIGHTS: 0.01
-VALIDATION:
-  SUMMARY_STEPS: 5
-  DATASETS: ['damon', 'rich', 'prox']
-  MAIN_DATASET: 'damon'

hot_analysis/.ipynb_checkpoints/hico_analysis-checkpoint.ipynb

@@ -1,307 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import json\n",
-    "import pandas as pd \n",
-    "import ipdb\n",
-    "import os\n",
-    "import pickle as pkl\n",
-    "import os.path as osp\n",
-    "import numpy as np\n",
-    "from PIL import Image\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Total images found: 9642\n",
-      "Images after KP filtering: 3895\n",
-      "['hake_train2015_HICO_train2015_00005476.jpg', 'hake_train2015_HICO_train2015_00008329.jpg', 'hake_train2015_HICO_train2015_00008027.jpg', 'hake_train2015_HICO_train2015_00013408.jpg', 'hake_train2015_HICO_train2015_00010656.jpg']\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Load Agniv VITpose-base hico filtering\n",
-    "filter_path = './agniv_pose_filter/hico.npy'\n",
-    "pose_md = np.load(filter_path, allow_pickle=True)\n",
-    "pose_md = pose_md.item()\n",
-    "filter_img_names = {}\n",
-    "\n",
-    "print(f'Total images found: {len(pose_md)}')\n",
-    "\n",
-    "# Filter out images with < 10 visible keypoints \n",
-    "kp_thresh = 10\n",
-    "\n",
-    "for imgname, pose_num in pose_md.items():\n",
-    "    if pose_num > kp_thresh:\n",
-    "        filter_img_names[imgname] = pose_num\n",
-    "        \n",
-    "print(f'Images after KP filtering: {len(filter_img_names)}')\n",
-    "\n",
-    "print(list(filter_img_names.keys())[:5])\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Load Agniv VITpose-base hot dict\n",
-    "# filter_path = \"./agniv_pose_filter/hot_dict.pkl\"\n",
-    "# with open(filter_path, 'rb') as f:\n",
-    "#     pose_md_dict = pkl.load(f)\n",
-    "    \n",
-    "# hico_dict = {}\n",
-    "\n",
-    "# for k, v in pose_md_dict.items():\n",
-    "#     if 'hake' in k:\n",
-    "#         hico_dict[k] = v\n",
-    "    \n",
-    "# print(f'Total images found: {len(hico_dict)}')\n",
-    "\n",
-    "# # Filter out images with < 10 visible keypoints \n",
-    "# kp_thresh = 10\n",
-    "\n",
-    "# filter_img_names = {}\n",
-    "\n",
-    "# for imgname, kp_md in hico_dict.items():\n",
-    "#     if kp_md == 0:\n",
-    "#         continue\n",
-    "#     if kp_md[\"num_persons\"] == 1 and kp_md[\"num_kpt\"][0.5][0] > kp_thresh:\n",
-    "#         filter_img_names[imgname] = kp_md[\"num_kpt\"][0.5][0]\n",
-    "        \n",
-    "# print(f'Images after KP filtering: {len(filter_img_names)}')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "       0         1               2\n",
-      "0      1  airplane           board\n",
-      "1      2  airplane          direct\n",
-      "2      3  airplane            exit\n",
-      "3      4  airplane             fly\n",
-      "4      5  airplane         inspect\n",
-      "..   ...       ...             ...\n",
-      "595  596     zebra            feed\n",
-      "596  597     zebra            hold\n",
-      "597  598     zebra             pet\n",
-      "598  599     zebra           watch\n",
-      "599  600     zebra  no_interaction\n",
-      "\n",
-      "[600 rows x 3 columns]\n"
-     ]
-    }
-   ],
-   "source": [
-    "\n",
-    "hico_annot = json.load(open('/ps/project/datasets/HICO/hico-image-level/hico-training-set-image-level.json', 'rb'))\n",
-    "hoi_mapping = pd.read_csv('/ps/project/datasets/HICO/hico-image-level/hico_hoi_list.txt', header=None, delim_whitespace=True)\n",
-    "print(hoi_mapping)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Final number of images 3154\n"
-     ]
-    }
-   ],
-   "source": [
-    "version = '1'\n",
-    "out_dir = f'./filtered_data/v_{version}'\n",
-    "os.makedirs(out_dir, exist_ok=True)\n",
-    "\n",
-    "objectwise_img_names = {}\n",
-    "imgwise_object_names = {}\n",
-    "img_dir = '/ps/project/datasets/HICO/hico_20150920/images/train2015'\n",
-    "\n",
-    "bad_object_names = ['bear', 'bird', 'cat', 'cow', \n",
-    "                    'dog', 'elephant', 'giraffe', 'horse', \n",
-    "                   'mouse', 'person', 'sheep', 'zebra' ]\n",
-    "bad_action_names = ['buy', 'chase', 'direct', 'greet', 'herd', 'hose',\n",
-    "                   'hug', 'hunt', 'milk', 'no_interaction', 'pet', 'point', 'teach',\n",
-    "                   'watch', 'wave']\n",
-    "\n",
-    "for i, (img_name, img_md) in enumerate(hico_annot.items()):\n",
-    "    \n",
-    "    # Apply keypoint number filtering on the images \n",
-    "    full_img_name = 'hake_train2015_' + img_name\n",
-    "    if full_img_name not in filter_img_names.keys():\n",
-    "        continue\n",
-    "    \n",
-    "    # show the image\n",
-    "    if i < 0:\n",
-    "        img = Image.open(osp.join(img_dir,img_name))\n",
-    "        display(img)\n",
-    "    \n",
-    "    obj_names = []\n",
-    "    action_names = []\n",
-    "    kp_num = filter_img_names[full_img_name]\n",
-    "    \n",
-    "    # travel through all hoi in the metadata, save obj_names and action_names for the hois\n",
-    "    for hoi_id in img_md['hoi_id']:\n",
-    "        img_md_row = hoi_mapping.loc[hoi_mapping[0] == hoi_id].iloc[0]\n",
-    "\n",
-    "        obj_name = img_md_row[1]\n",
-    "        if obj_name in bad_object_names:\n",
-    "            continue\n",
-    "        action_name = img_md_row[2]\n",
-    "        if action_name in bad_action_names:\n",
-    "            continue\n",
-    "            \n",
-    "        obj_names.append(obj_name)\n",
-    "        action_names.append(action_name)\n",
-    "        \n",
-    "    if len(set(obj_names)) == 0 or len(action_names) == 0:\n",
-    "        continue\n",
-    "    \n",
-    "    imgwise_object_names.setdefault(full_img_name,[]).extend(list(set(obj_names)))\n",
-    "    \n",
-    "# #     # Display images with multiple objects\n",
-    "#     if len(set(obj_names)) > 1:\n",
-    "#         print(img_name)\n",
-    "#         print(obj_names)\n",
-    "#         print(action_names)\n",
-    "#         print(f'Number of Kps: {kp_num}')\n",
-    "#         img = Image.open(osp.join(img_dir,img_name))\n",
-    "#         display(img)\n",
-    "            \n",
-    "    for obj_name in set(obj_names):\n",
-    "        objectwise_img_names.setdefault(obj_name,[]).append(full_img_name)\n",
-    "        \n",
-    "print(f'Final number of images {len(imgwise_object_names)}')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "# Save the imagewise_object dict\n",
-    "out_path = osp.join(out_dir, 'object_per_image_dict.json')\n",
-    "with open(out_path, 'w') as fp:\n",
-    "    json.dump(imgwise_object_names, fp)\n",
-    "    print(f'saved at {out_path}')\n",
-    "    \n",
-    "# # save image_list \n",
-    "# out_path = osp.join(out_dir, 'hico_imglist_all_140223.txt')\n",
-    "# with open(out_path, 'w') as f:\n",
-    "#     f.write('\\n'.join(imgwise_object_names.keys()))\n",
-    "#     print(f'saved at {out_path}')\n",
-    "\n",
-    "\n",
-    "# Save the object_wise dict\n",
-    "out_path = osp.join(out_dir, 'imgnames_per_object_dict.json')\n",
-    "with open(out_path, 'w') as fp:\n",
-    "    json.dump(objectwise_img_names, fp)\n",
-    "    print(f'saved at {out_path}')\n",
-    "\n",
-    "    \n",
-    "\n",
-    "    "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns\n",
-    "\n",
-    "# sort the dictionary \n",
-    "objectwise_img_names = dict(sorted(objectwise_img_names.items(), key=lambda x: len(x[1]), reverse=True))\n",
-    "\n",
-    "# Extract object names and image counts\n",
-    "obj_names = list(objectwise_img_names.keys())\n",
-    "img_counts = [len(objectwise_img_names[obj]) for obj in objectwise_img_names]\n",
-    "print(sum(img_counts))\n",
-    "\n",
-    "# Create bar plot\n",
-    "sns.barplot(x=obj_names, y=img_counts)\n",
-    "\n",
-    "# Add x-axis and y-axis labels\n",
-    "plt.xlabel('Object')\n",
-    "plt.ylabel('Number of Images')\n",
-    "\n",
-    "plt.xticks(rotation=45, ha='right', fontsize=3)\n",
-    "\n",
-    "# Save the plot as a high-resolution image file\n",
-    "out_path = osp.join(out_dir, 'image_per_object_category.png')\n",
-    "plt.savefig(out_path, dpi=300)\n",
-    "\n",
-    "# Show plot\n",
-    "plt.show()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "    "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

hot_analysis/.ipynb_checkpoints/vcoco_analysis-checkpoint.ipynb

@@ -1,276 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import json\n",
-    "import pandas as pd \n",
-    "import ipdb\n",
-    "import os\n",
-    "import pickle as pkl\n",
-    "import os.path as osp\n",
-    "import numpy as np\n",
-    "from PIL import Image"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Total images found: 5459\n",
-      "Images after KP filtering: 2386\n",
-      "['vcoco_000000051899.jpg', 'vcoco_000000093127.jpg', 'vcoco_000000455665.jpg', 'vcoco_000000248389.jpg', 'vcoco_000000403947.jpg']\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Load Agniv VITpose-base hot dict\n",
-    "filter_path = \"./agniv_pose_filter/hot_dict.pkl\"\n",
-    "with open(filter_path, 'rb') as f:\n",
-    "    pose_md_dict = pkl.load(f)\n",
-    "    \n",
-    "vcoco_dict = {}\n",
-    "\n",
-    "for k, v in pose_md_dict.items():\n",
-    "    if 'vcoco' in k:\n",
-    "        vcoco_dict[k] = v\n",
-    "    \n",
-    "print(f'Total images found: {len(vcoco_dict)}')\n",
-    "\n",
-    "# Filter out images with < 10 visible keypoints \n",
-    "kp_thresh = 10\n",
-    "\n",
-    "filter_img_names = {}\n",
-    "\n",
-    "for imgname, kp_md in vcoco_dict.items():\n",
-    "    if kp_md == 0:\n",
-    "        continue\n",
-    "    if kp_md[\"num_persons\"] == 1 and kp_md[\"num_kpt\"][0.5][0] > kp_thresh:\n",
-    "        filter_img_names[imgname] = kp_md[\"num_kpt\"][0.5][0]\n",
-    "        \n",
-    "print(f'Images after KP filtering: {len(filter_img_names)}')\n",
-    "\n",
-    "print(list(filter_img_names.keys())[:5])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 35,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "loading annotations into memory...\n",
-      "Done (t=1.30s)\n",
-      "creating index...\n",
-      "index created!\n",
-      "Final number of images 2368\n"
-     ]
-    }
-   ],
-   "source": [
-    "from pycocotools.coco import COCO\n",
-    "version = '1'\n",
-    "out_dir = f'./filtered_data/v_{version}/vcoco'\n",
-    "os.makedirs(out_dir, exist_ok=True)\n",
-    "\n",
-    "coco_dir = '/is/cluster/work/stripathi/pycharm_remote/v-coco/data'\n",
-    "coco = COCO(os.path.join(coco_dir, 'instances_vcoco_all_2014.json'))\n",
-    "\n",
-    "imgwise_object_names = {}\n",
-    "img_dir = '/ps/project/datasets/HOT/Contact_Data/images/training/'\n",
-    "\n",
-    "bad_object_names = ['bird', 'cat', 'dog', 'horse', 'sheep', 'cow', \n",
-    "                    'elephant', 'bear', 'zebra', 'giraffe']\n",
-    "\n",
-    "# # Get all coco objects\n",
-    "# count = 0\n",
-    "# for id in range(91):\n",
-    "#     try: \n",
-    "#         print(coco.loadCats(id))\n",
-    "#         count += 1\n",
-    "#     except:\n",
-    "#         print(f'ID:{id} does not exist')\n",
-    "#         continue\n",
-    "# print(count)\n",
-    "\n",
-    "objectwise_img_names = {}\n",
-    "for img_name in filter_img_names.keys():\n",
-    "    img_id = int(os.path.splitext(img_name.split('_')[-1])[0])\n",
-    "    ann_ids = coco.getAnnIds([img_id])\n",
-    "    anns = coco.loadAnns(ann_ids)\n",
-    "    object_list = []\n",
-    "    for ann in anns:\n",
-    "        object_cat = coco.loadCats(ann[\"category_id\"])\n",
-    "        if len(object_cat) > 1:\n",
-    "            ipdb.set_trace()\n",
-    "        object_name = object_cat[0]['name']\n",
-    "        if object_name in bad_object_names:\n",
-    "            continue\n",
-    "        if object_name != 'person':\n",
-    "            object_list.append(object_name)\n",
-    "    if len(object_list) != 0:\n",
-    "        imgwise_object_names[img_name] = list(set(object_list))\n",
-    "        \n",
-    "    for obj_name in set(object_list):\n",
-    "        objectwise_img_names.setdefault(obj_name,[]).append(img_name)\n",
-    "        \n",
-    "#         # Visualize images \n",
-    "#         print(img_name)\n",
-    "#         print(list(set(object_list)))\n",
-    "#         img = Image.open(osp.join(img_dir,img_name))\n",
-    "#         display(img)\n",
-    "    \n",
-    "    \n",
-    "print(f'Final number of images {len(imgwise_object_names)}')\n",
-    "    \n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 36,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "saved at ./filtered_data/v_1/vcoco/object_per_image_dict.json\n",
-      "saved at ./filtered_data/v_1/vcoco/vcoco_imglist_all_170223.txt\n",
-      "saved at ./filtered_data/v_1/vcoco/imgnames_per_object_dict.json\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Save the imagewise_object dict\n",
-    "out_path = osp.join(out_dir, 'object_per_image_dict.json')\n",
-    "with open(out_path, 'w') as fp:\n",
-    "    json.dump(imgwise_object_names, fp)\n",
-    "    print(f'saved at {out_path}')\n",
-    "    \n",
-    "# save image_list \n",
-    "out_path = osp.join(out_dir, 'vcoco_imglist_all_170223.txt')\n",
-    "with open(out_path, 'w') as f:\n",
-    "    f.write('\\n'.join(imgwise_object_names.keys()))\n",
-    "    print(f'saved at {out_path}')\n",
-    "\n",
-    "\n",
-    "# Save the object_wise dict\n",
-    "out_path = osp.join(out_dir, 'imgnames_per_object_dict.json')\n",
-    "with open(out_path, 'w') as fp:\n",
-    "    json.dump(objectwise_img_names, fp)\n",
-    "    print(f'saved at {out_path}')\n",
-    "\n",
-    "    \n",
-    "\n",
-    "    "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "5072\n"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 432x288 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns\n",
-    "\n",
-    "# sort the dictionary \n",
-    "objectwise_img_names = dict(sorted(objectwise_img_names.items(), key=lambda x: len(x[1]), reverse=True))\n",
-    "\n",
-    "# Extract object names and image counts\n",
-    "obj_names = list(objectwise_img_names.keys())\n",
-    "img_counts = [len(objectwise_img_names[obj]) for obj in objectwise_img_names]\n",
-    "print(sum(img_counts))\n",
-    "\n",
-    "# Create bar plot\n",
-    "sns.barplot(x=obj_names, y=img_counts)\n",
-    "\n",
-    "# Add x-axis and y-axis labels\n",
-    "plt.xlabel('Object')\n",
-    "plt.ylabel('Number of Images')\n",
-    "\n",
-    "plt.xticks(rotation=45, ha='right', fontsize=3)\n",
-    "\n",
-    "# Save the plot as a high-resolution image file\n",
-    "out_path = osp.join(out_dir, 'image_per_object_category.png')\n",
-    "plt.savefig(out_path, dpi=300)\n",
-    "\n",
-    "# Show plot\n",
-    "plt.show()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "    "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

hot_analysis/agniv_pose_filter/hico.npy

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b01acf6e31dad34eb1e48277e227ea0668f17905f55eae44b640cc1d14a9e41c
-size 520245

hot_analysis/agniv_pose_filter/hot.npy

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:64872b84670cb2ec643f1649e1a7926aed950adcb8f6f952916924bc4ab10f37
-size 731363

hot_analysis/agniv_pose_filter/hot_dict.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f0c0a6e35bf87e98327189ef8d732aa19b0d1c85c963c1ee348e1e466864845e
-size 3679000

hot_analysis/agniv_pose_filter/pq_wnp.npy

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7cad59d5aaf077141d60a492c3784d8994d53f4dfd020f9eb4e11b3e430ef65d
-size 25433

hot_analysis/agniv_pose_filter/vcoco.npy

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:14cc34940ff4a61cfc952d8c5b98e0e7b1a58392177198fa4589f8b2bcead02a
-size 184801

hot_analysis/count_objects_per_img.py

@@ -1,35 +0,0 @@
-# get average number of objects per image
-import os.path as osp
-import json
-import plotly.express as px
-import plotly.io as pio
-
-version = '1'
-dir = '/is/cluster/work/stripathi/pycharm_remote/dca_contact/hot_analysis/'
-out_dir_hico = osp.join(dir, f'filtered_data/v_{version}/hico')
-out_dir_vcoco = osp.join(dir, f'filtered_data/v_{version}/vcoco')
-
-imgwise_obj_dict_hico = osp.join(out_dir_hico, 'object_per_image_dict.json')
-imgwise_obj_dict_vcoco = osp.join(out_dir_vcoco, 'object_per_image_dict.json')
-
-with open(imgwise_obj_dict_hico, 'r') as fp:
-    imgwise_obj_dict_hico = json.load(fp)
-with open(imgwise_obj_dict_vcoco, 'r') as fp:
-    imgwise_obj_dict_vcoco = json.load(fp)
-
-# combine the dicts
-imgwise_obj_dict = imgwise_obj_dict_hico.copy()
-imgwise_obj_dict.update(imgwise_obj_dict_vcoco)
-
-# get average length of object in the object per image key
-avg_obj_per_img = sum([len(v) for v in imgwise_obj_dict.values()]) / len(imgwise_obj_dict)
-print(f'Average number of objects per image: {avg_obj_per_img}')
-
-# get average searately for hico and vcoco
-avg_obj_per_img_hico = sum([len(v) for v in imgwise_obj_dict_hico.values()]) / len(imgwise_obj_dict_hico)
-print(f'Average number of objects per image in hico: {avg_obj_per_img_hico}')
-
-avg_obj_per_img_vcoco = sum([len(v) for v in imgwise_obj_dict_vcoco.values()])  / len(imgwise_obj_dict_vcoco)
-print(f'Average number of objects per image in vcoco: {avg_obj_per_img_vcoco}')
-
-

hot_analysis/create_combined_objectwise_plots.ipynb

@@ -1,291 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "1738c3a5",
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "import os.path as osp\n",
-    "import json\n",
-    "import os\n",
-    "\n",
-    "version = '1'\n",
-    "out_dir_hico = f'./filtered_data/v_{version}/hico'\n",
-    "out_dir_vcoco = f'./filtered_data/v_{version}/vcoco'\n",
-    "out_dir_phosa = f'./filtered_data/v_{version}/phosa_split'\n",
-    "out_dir_behave = f'./filtered_data/v_{version}/behave_split'\n",
-    "\n",
-    "objectwise_img_dict_hico = osp.join(out_dir_hico, 'imgnames_per_object_dict.json')\n",
-    "objectwise_img_dict_vcoco = osp.join(out_dir_vcoco, 'imgnames_per_object_dict.json')\n",
-    "\n",
-    "with open(objectwise_img_dict_hico, 'r') as fp:\n",
-    "    objectwise_img_dict_hico = json.load(fp)\n",
-    "with open(objectwise_img_dict_vcoco, 'r') as fp:\n",
-    "    objectwise_img_dict_vcoco = json.load(fp)\n",
-    "\n",
-    "# sort the dictionary \n",
-    "objectwise_img_names1 = dict(sorted(objectwise_img_dict_hico.items(), key=lambda x: len(x[1]), reverse=True))\n",
-    "\n",
-    "# # Extract object names and image counts\n",
-    "# obj_names1 = list(objectwise_img_names_hico.keys())\n",
-    "# print(sorted(obj_names1))\n",
-    "# image_count1 = [len(objectwise_img_names_hico[obj]) for obj in objectwise_img_names_hico]\n",
-    "# print(sum(image_count1))\n",
-    "\n",
-    "# sort the dictionary \n",
-    "objectwise_img_names2 = dict(sorted(objectwise_img_dict_vcoco.items(), key=lambda x: len(x[1]), reverse=True))\n",
-    "\n",
-    "# # Extract object names and image counts\n",
-    "# obj_names2 = list(objectwise_img_names_vcoco.keys())\n",
-    "# print(sorted(obj_names2))\n",
-    "# image_count2 = [len(objectwise_img_names_vcoco[obj]) for obj in objectwise_img_names_vcoco]\n",
-    "# print(sum(image_count2))\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "2d6ad5ed",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "2119\n",
-      "saved at ./filtered_data/v_1/phosa_split/imgnames_per_object_dict.json\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Extract image list for object in PHOSA\n",
-    "def merge_dictionaries(dict1, dict2):\n",
-    "    merged_dict = {}\n",
-    "\n",
-    "    # Merge values for common keys\n",
-    "    for key in set(dict1.keys()) | set(dict2.keys()):\n",
-    "        merged_dict[key] = list(set(dict1.get(key, [])) | set(dict2.get(key, [])))\n",
-    "\n",
-    "    return merged_dict\n",
-    "\n",
-    "def filter_dictionary(dictionary, keys):\n",
-    "    filtered_dict = {key: dictionary[key] for key in keys if key in dictionary}\n",
-    "    return filtered_dict\n",
-    "\n",
-    "phosa_object_names = [\"bat\", \"bench\", \"bicycle\", \"laptop\", \"motorcycle\", \"skateboard\", \"surfboard\", \"tennis\"]\n",
-    "combined_objectwise_img_names = merge_dictionaries(objectwise_img_names1, objectwise_img_names2)\n",
-    "phosa_objectwise_img_names = filter_dictionary(combined_objectwise_img_names, phosa_object_names)\n",
-    "net_img_count = 0\n",
-    "for v in phosa_objectwise_img_names.values():\n",
-    "    net_img_count += len(v)\n",
-    "print(net_img_count)\n",
-    "# Save the object_wise dict\n",
-    "os.makedirs(out_dir_phosa, exist_ok=True)\n",
-    "out_path_phosa = osp.join(out_dir_phosa, 'imgnames_per_object_dict.json')\n",
-    "with open(out_path_phosa, 'w') as fp:\n",
-    "    json.dump(phosa_objectwise_img_names, fp)\n",
-    "    print(f'saved at {out_path_phosa}')\n",
-    "    \n",
-    "    "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "3f2a5e62",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "saved at ./filtered_data/v_1/behave_split/imgnames_per_object_dict.json\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Extract image list for object in CHORE\n",
-    "\n",
-    "behave_object_names_original = [\"backpack\", \"basketball\", \"boxlarge\", \"boxlong\", \"boxmedium\", \"boxsmall\", \"boxtiny\", \"chairblack\", \"chairwood\", \"keyboard\", \"monitor\", \"plasticcontainer\", \"stool\", \"suitcase\", \"tablesmall\", \"tablesquare\", \"toolbox\", \"trashbin\", \"yogaball\", \"yogamat\"]\n",
-    "behave_object_names_in_hot = [\"backpack\", \"chair\", \"keyboard\", \"suitcase\"]\n",
-    "\n",
-    "combined_objectwise_img_names = merge_dictionaries(objectwise_img_names1, objectwise_img_names2)\n",
-    "behave_objectwise_img_names = filter_dictionary(combined_objectwise_img_names, behave_object_names_in_hot)\n",
-    "net_img_count = 0\n",
-    "for v in behave_objectwise_img_names.values():\n",
-    "    net_img_count += len(v)\n",
-    "\n",
-    "# Save the object_wise dict\n",
-    "os.makedirs(out_dir_behave, exist_ok=True)\n",
-    "out_path_behave = osp.join(out_dir_behave, 'imgnames_per_object_dict.json')\n",
-    "with open(out_path_behave, 'w') as fp:\n",
-    "    json.dump(behave_objectwise_img_names, fp)\n",
-    "    print(f'saved at {out_path_behave}')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "730e9ac2",
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "ModuleNotFoundError",
-     "evalue": "No module named 'seaborn'",
-     "output_type": "error",
-     "traceback": [
-      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
-      "\u001B[0;31mModuleNotFoundError\u001B[0m                       Traceback (most recent call last)",
-      "Cell \u001B[0;32mIn[3], line 2\u001B[0m\n\u001B[1;32m      1\u001B[0m \u001B[38;5;28;01mimport\u001B[39;00m \u001B[38;5;21;01mmatplotlib\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mpyplot\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m \u001B[38;5;21;01mplt\u001B[39;00m\n\u001B[0;32m----> 2\u001B[0m \u001B[38;5;28;01mimport\u001B[39;00m \u001B[38;5;21;01mseaborn\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m \u001B[38;5;21;01msns\u001B[39;00m\n\u001B[1;32m      4\u001B[0m \u001B[38;5;66;03m# sort the dictionary \u001B[39;00m\n\u001B[1;32m      5\u001B[0m objectwise_img_names1 \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mdict\u001B[39m(\u001B[38;5;28msorted\u001B[39m(objectwise_img_names1\u001B[38;5;241m.\u001B[39mitems(), key\u001B[38;5;241m=\u001B[39m\u001B[38;5;28;01mlambda\u001B[39;00m x: \u001B[38;5;28mlen\u001B[39m(x[\u001B[38;5;241m1\u001B[39m]), reverse\u001B[38;5;241m=\u001B[39m\u001B[38;5;28;01mTrue\u001B[39;00m))\n",
-      "\u001B[0;31mModuleNotFoundError\u001B[0m: No module named 'seaborn'"
-     ]
-    }
-   ],
-   "source": [
-    "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns\n",
-    "\n",
-    "# sort the dictionary \n",
-    "objectwise_img_names1 = dict(sorted(objectwise_img_names1.items(), key=lambda x: len(x[1]), reverse=True))\n",
-    "\n",
-    "# Extract object names and image counts\n",
-    "obj_names1 = list(objectwise_img_names1.keys())\n",
-    "print(obj_names1)\n",
-    "img_counts1 = [len(objectwise_img_names1[obj]) for obj in objectwise_img_names1]\n",
-    "print(sum(img_counts1))\n",
-    "\n",
-    "# sort the dictionary \n",
-    "objectwise_img_names2 = dict(sorted(objectwise_img_names2.items(), key=lambda x: len(x[1]), reverse=True))\n",
-    "\n",
-    "# Extract object names and image counts\n",
-    "obj_names2 = list(objectwise_img_names2.keys())\n",
-    "print(obj_names2)\n",
-    "img_counts2 = [len(objectwise_img_names2[obj]) for obj in objectwise_img_names2]\n",
-    "print(sum(img_counts2))\n",
-    "\n",
-    "# Create a figure with two subplots\n",
-    "fig, axs = plt.subplots(nrows=2, sharex=True, figsize=(10, 8))\n",
-    "\n",
-    "# Plot the first graph in the first subplot\n",
-    "sns.barplot(x=obj_names1, y=img_counts1, ax=axs[0])\n",
-    "\n",
-    "# Add y-axis label to the first subplot\n",
-    "axs[0].set_ylabel('Number of Images')\n",
-    "\n",
-    "# Set the rotation and alignment of x-tick labels in the first subplot\n",
-    "axs[0].tick_params(axis='x', rotation=45)\n",
-    "\n",
-    "# Plot the second graph in the second subplot\n",
-    "sns.barplot(x=obj_names2, y=img_counts2, ax=axs[1])\n",
-    "\n",
-    "# Add x-axis and y-axis labels to the second subplot\n",
-    "axs[1].set_xlabel('Object')\n",
-    "axs[1].set_ylabel('Number of Images')\n",
-    "\n",
-    "# Set the rotation and alignment of x-tick labels in the second subplot\n",
-    "axs[1].tick_params(axis='x', rotation=45)\n",
-    "\n",
-    "# Save the plot as a high-resolution image file\n",
-    "out_path = osp.join(out_dir, 'image_per_object_category.png')\n",
-    "plt.savefig(out_path, dpi=300)\n",
-    "\n",
-    "# Show the plot\n",
-    "plt.show()\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "23c503dd",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/tmp/ipykernel_135310/1442551168.py:22: UserWarning: FixedFormatter should only be used together with FixedLocator\n",
-      "  ax.set_xticklabels(X1)\n"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 1000x800 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "import matplotlib\n",
-    "import matplotlib.pyplot as plt\n",
-    "import numpy as np\n",
-    "import seaborn as sns\n",
-    "\n",
-    "# Create data\n",
-    "X1 = ['A', 'B', 'C', 'D', 'E']\n",
-    "Y1 = [10, 15, 20, 25, 30]\n",
-    "Y2 = [20, 25, 30, 35, 40]\n",
-    "\n",
-    "# Set color scheme and font\n",
-    "colors = sns.color_palette(\"Blues\", 2)\n",
-    "\n",
-    "# Create bar plot\n",
-    "fig, ax = plt.subplots(figsize=(10, 8))\n",
-    "ax.bar(X1, Y1, color=colors[0], edgecolor='white', linewidth=1)\n",
-    "ax.bar(X1, Y2, bottom=Y1, color=colors[1], edgecolor='white', linewidth=1)\n",
-    "\n",
-    "# Set axis labels and ticks\n",
-    "ax.set_xlabel('X1')\n",
-    "ax.set_ylabel('Y')\n",
-    "ax.set_xticklabels(X1)\n",
-    "ax.tick_params(axis='both', which='major', labelsize=14)\n",
-    "ax.grid(axis='y', alpha=0.4)\n",
-    "\n",
-    "# Add legend and title\n",
-    "ax.legend(['Y1', 'Y2'], loc='upper left')\n",
-    "ax.set_title('Vertical stacked bar graph of Y1 and Y2')\n",
-    "\n",
-    "# Save the graph as PDF or PNG\n",
-    "plt.savefig('vertical_stacked_bar_graph.png', dpi=300, bbox_inches='tight')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4c055ec7",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

hot_analysis/create_part_probability_mesh.py

@@ -1,86 +0,0 @@
-import numpy as np
-import os
-import json
-import trimesh
-import seaborn as sns
-
-
-# Load the combined dca train, val and test npzs
-dir = '/is/cluster/work/stripathi/pycharm_remote/dca_contact/data/dataset_extras'
-trainval_npz = np.load(os.path.join(dir, 'hot_dca_trainval.npz'), allow_pickle=True)
-test_npz = np.load(os.path.join(dir, 'hot_dca_test.npz'), allow_pickle=True)
-
-# combine the two npz
-combined_npz = {}
-for key in trainval_npz.keys():
-    combined_npz[key] = np.concatenate([trainval_npz[key], test_npz[key]], axis=0)
-
-segmentation_path = 'data/smpl_vert_segmentation.json'
-with open(segmentation_path, 'rb') as f:
-    part_segmentation = json.load(f)
-
-combine_keys = {'leftFoot': ['leftToeBase'],
-                'rightFoot': ['rightToeBase'],
-                'leftHand': ['leftHandIndex1'],
-                'rightHand': ['rightHandIndex1'],
-                'spine': ['spine1', 'spine2'],
-                'head': ['neck'],}
-
-for key in combine_keys:
-    for subkey in combine_keys[key]:
-        part_segmentation[key] += part_segmentation[subkey]
-        del part_segmentation[subkey]
-
-# reverse the part segmentation
-part_segmentation_rev = {}
-for part in part_segmentation:
-    for vert in part_segmentation[part]:
-        part_segmentation_rev[vert] = part
-
-# count the number of contact instances per vertex
-per_vert_contact_count = np.zeros(6890)
-for cls in combined_npz['contact_label']:
-    per_vert_contact_count += cls
-
-# calculate the maximum contact count per part
-part_contact_max = {}
-for part in part_segmentation:
-    part_contact_max[part] = np.max(per_vert_contact_count[part_segmentation[part]])
-
-# calculate the contact probability globally
-contact_prob = np.zeros(6890)
-for vid in range(6890):
-    contact_prob[vid] = (per_vert_contact_count[vid] / max(per_vert_contact_count)) ** 0.3
-
-# save the contact probability mesh
-outdir = "/is/cluster/work/stripathi/pycharm_remote/dca_contact/hot_analysis"
-
-# load template smpl mesh
-mesh = trimesh.load_mesh('data/smpl/smpl_neutral_tpose.ply')
-vertex_colors = trimesh.visual.interpolate(contact_prob, 'jet')
-# set the vertex colors of the mesh
-mesh.visual.vertex_colors = vertex_colors
-# save the mesh
-out_path = os.path.join(outdir, "contact_probability_mesh.obj")
-mesh.export(out_path)
-
-# # calculate the contact probability per part
-# contact_prob = np.zeros(6890)
-# for vid in range(6890):
-#     if 'Hand' in part_segmentation_rev[vid]:
-#     contact_prob[vid] = (per_vert_contact_count[vid] / part_contact_max[part_segmentation_rev[vid]]) ** 0.4 if 'Hand' not in part_segmentation_rev[vid] else (per_vert_contact_count[vid] / part_contact_max[part_segmentation_rev[vid]]) ** 0.8
-#
-# # save the contact probability mesh
-# outdir = "/is/cluster/work/stripathi/pycharm_remote/dca_contact/hot_analysis"
-#
-# # load template smpl mesh
-# mesh = trimesh.load_mesh('data/smpl/smpl_neutral_tpose.ply')
-# vertex_colors = trimesh.visual.interpolate(contact_prob, 'jet')
-# # set the vertex colors of the mesh
-# mesh.visual.vertex_colors = vertex_colors
-# # save the mesh
-# out_path = os.path.join(outdir, "contact_probability_mesh_part.obj")
-# mesh.export(out_path)
-
-
-

hot_analysis/damon_qc_stats/compute_accuracy_iou_damon.py

@@ -1,59 +0,0 @@
-# load amt csv, go through each line in vertices, combine the vertices for each object label and then compute the iou with GT from RICH and PROX
-import pandas as pd
-import numpy as np
-
-# load csv
-csv_path = './quality_assurance_accuracy.csv'
-df = pd.read_csv(csv_path)
-
-# load gt npz
-gt_path = './qa_accuracy_gt_contact_combined.npz'
-gt = np.load(gt_path)
-
-def compute_iou(pred_verts, gt_verts):
-    if len(pred_verts) != 0:
-        intersect = list(set(pred_verts) & set(gt_verts))
-        iou = len(intersect) / (len(pred_verts) + len(gt_verts) - len(intersect))
-    else:
-        iou = 0
-    return iou
-
-all_ious = []
-# for loop each row in df
-for index, row in df.iterrows():
-    combined_annotation_ids = []
-    imgname = []
-    # get vertices
-    annotation_dict = eval(row['vertices'])
-    worker_id = row['WorkerId']
-    # single for loop in the dictionary
-    for im, anno in annotation_dict.items():
-        imgname.append(im)
-        for ann in anno:
-            # single for loop in the dict
-            for k, v in ann.items():
-                combined_annotation_ids.extend(v)
-    # remove repeated values
-    combined_annotation_ids = list(set(combined_annotation_ids))
-
-    assert len(imgname) == 1
-    imgname = imgname[0]
-
-    # get gt for the imgname
-    gt_ids = gt[imgname]
-    if 'prox' in imgname:
-        continue
-
-    # compute iou
-    iou = compute_iou(combined_annotation_ids, gt_ids)
-    print('worker id: ', worker_id, 'imgname: ', imgname, 'iou: ', iou)
-    all_ious.append(iou)
-
-# compute mean iou
-mean_iou = np.mean(all_ious)
-print('mean iou: ', mean_iou)
-
-
-
-
-

hot_analysis/damon_qc_stats/compute_fleiss_kappa_damon.py

@@ -1,111 +0,0 @@
-import numpy as np
-import pandas as pd
-from scipy.stats import chi2
-
-
-def correct_supporting(vertices):
-    # Copy vertices from objects to supporting since the dropdown option was missing in the QA app
-    def add_supporting(verts, object_name):
-        temp_supporting_vids = []
-        supporting_vid = -1
-        for id, v_i in enumerate(verts):
-            # single key dict
-            for k, v in v_i.items():
-                if k == object_name:
-                    temp_supporting_vids = v
-                if k == 'SUPPORTING':
-                    supporting_vid = id
-        if supporting_vid != -1:
-            # append to supporting
-            verts[supporting_vid]['SUPPORTING'] += temp_supporting_vids
-        return verts
-
-    # correct supporting contacts
-    for i, vert in enumerate(vertices):
-        for k, v in vert.items():
-            if k == 'hot/training/hake_train2015_HICO_train2015_00000019.jpg':
-                # copy bicycle contacts to supporting
-                v = add_supporting(v, 'BICYCLE')
-            if k == 'hot/training/hake_train2015_HICO_train2015_00000020.jpg':
-                # copy skateboard contacts to supporting
-                v = add_supporting(v, 'SKATEBOARD')
-            if k == 'hot/training/hake_train2015_HICO_train2015_00000942':
-                # copy bench contacts to supporting
-                v = add_supporting(v, 'BENCH')
-
-            # combine all vert_ids into a single list no matter the object
-            v = {ki: vi for d in v for ki, vi in d.items()}
-            v = [vi for k, vi in v.items()]
-            v = [item for sublist in v for item in sublist]
-            v = list(set(v))
-            # binarize the list to a numpy array
-            v_np = np.zeros(6890)
-            v_np[v] = 1
-            vert[k] = v_np
-        vertices[i] = vert
-    return vertices
-
-def fleiss_kappa_per_img(vertices):
-    """
-    Compute Fleiss' kappa per imagename
-    Parameters
-    ----------
-    vertices : list of np arrays where each array is of shape (6890,) and 1 indicates a vertex is selected
-    """
-    n = len(vertices)  # number of raters
-    N = 6890  # number of images
-    k = 2  # number of categories
-
-    # compute the observed agreement
-    M = np.zeros((N, k))
-
-    for i in range(k):
-        M[:, i] = np.sum(vertices == i, axis=0)
-
-    assert np.sum(M) == N * n
-
-    # compute the expected agreement
-    p = np.sum(M, axis=0) / (N * n)
-    P = (np.sum(M * M, axis=1) - n) / (n * (n - 1))
-    Pbar = np.mean(P)
-    PbarE = np.sum(p * p)
-
-    # compute Fleiss' kappa
-    kappa = (Pbar - PbarE) / (1 - PbarE)
-    return kappa
-
-def fleiss_kappa(data):
-    """
-    Compute Fleiss' kappa per imagename
-    Parameters
-    ----------
-    data : list of dicts where keys are imgnames
-    """
-    imgnames = sorted(data[0].keys())
-    kappas = []
-    for img in imgnames:
-        kappa_data = []
-        for d in data:
-            kappa_data.append(d[img])
-        kappa_data = np.array(kappa_data)
-        kappa_img = fleiss_kappa_per_img(kappa_data)
-        print(f'Fleiss\' Kappa for {img}: {kappa_img}')
-        kappas.append(kappa_img)
-
-    # computer mean kappa
-    kappa = np.mean(kappas)
-    return kappa
-
-
-# Load the combined qa csv file
-csv_file = 'quality_assurance_fleiss.csv'
-df = pd.read_csv(csv_file)
-
-vertices = df['vertices'].values
-vertices = [eval(v) for v in vertices]
-
-vertices = correct_supporting(vertices)
-
-kappa = fleiss_kappa(vertices)
-
-print('Fleiss\' Kappa:', kappa)

hot_analysis/damon_qc_stats/qa_accuracy_gt_contact_combined.npz

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b34393328dae058aa12245f547ee954f48508bf0c4ed7ecbe40a674245ba5717
-size 456742

hot_analysis/filtered_data/v_1/vcoco/vcoco_imglist_all_170223.txt

@@ -1,2368 +0,0 @@
-vcoco_000000051899.jpg
-vcoco_000000093127.jpg
-vcoco_000000455665.jpg
-vcoco_000000248389.jpg
-vcoco_000000403947.jpg
-vcoco_000000418634.jpg
-vcoco_000000065161.jpg
-vcoco_000000504606.jpg
-vcoco_000000535135.jpg
-vcoco_000000284098.jpg
-vcoco_000000318785.jpg
-vcoco_000000003770.jpg
-vcoco_000000343002.jpg
-vcoco_000000491784.jpg
-vcoco_000000342013.jpg
-vcoco_000000335909.jpg
-vcoco_000000489121.jpg
-vcoco_000000552365.jpg
-vcoco_000000526681.jpg
-vcoco_000000477136.jpg
-vcoco_000000438861.jpg
-vcoco_000000033958.jpg
-vcoco_000000548029.jpg
-vcoco_000000520528.jpg
-vcoco_000000568604.jpg
-vcoco_000000160480.jpg
-vcoco_000000579466.jpg
-vcoco_000000459576.jpg
-vcoco_000000053347.jpg
-vcoco_000000548592.jpg
-vcoco_000000491215.jpg
-vcoco_000000335274.jpg
-vcoco_000000343803.jpg
-vcoco_000000343860.jpg
-vcoco_000000561810.jpg
-vcoco_000000313145.jpg
-vcoco_000000094766.jpg
-vcoco_000000386677.jpg
-vcoco_000000517349.jpg
-vcoco_000000430259.jpg
-vcoco_000000412301.jpg
-vcoco_000000306426.jpg
-vcoco_000000057782.jpg
-vcoco_000000068646.jpg
-vcoco_000000341818.jpg
-vcoco_000000024446.jpg
-vcoco_000000482362.jpg
-vcoco_000000087328.jpg
-vcoco_000000284846.jpg
-vcoco_000000098596.jpg
-vcoco_000000492648.jpg
-vcoco_000000343619.jpg
-vcoco_000000026552.jpg
-vcoco_000000578780.jpg
-vcoco_000000012817.jpg
-vcoco_000000298139.jpg
-vcoco_000000343104.jpg
-vcoco_000000262414.jpg
-vcoco_000000521956.jpg
-vcoco_000000506126.jpg
-vcoco_000000271490.jpg
-vcoco_000000233863.jpg
-vcoco_000000577880.jpg
-vcoco_000000146454.jpg
-vcoco_000000515704.jpg
-vcoco_000000280114.jpg
-vcoco_000000196108.jpg
-vcoco_000000368040.jpg
-vcoco_000000334941.jpg
-vcoco_000000194545.jpg
-vcoco_000000435141.jpg
-vcoco_000000547830.jpg
-vcoco_000000234642.jpg
-vcoco_000000122672.jpg
-vcoco_000000386912.jpg
-vcoco_000000132272.jpg
-vcoco_000000219629.jpg
-vcoco_000000445211.jpg
-vcoco_000000039958.jpg
-vcoco_000000270474.jpg
-vcoco_000000430428.jpg
-vcoco_000000269551.jpg
-vcoco_000000538003.jpg
-vcoco_000000096832.jpg
-vcoco_000000126097.jpg
-vcoco_000000411740.jpg
-vcoco_000000080117.jpg
-vcoco_000000106525.jpg
-vcoco_000000332722.jpg
-vcoco_000000036827.jpg
-vcoco_000000550870.jpg
-vcoco_000000305752.jpg
-vcoco_000000263083.jpg
-vcoco_000000476349.jpg
-vcoco_000000528621.jpg
-vcoco_000000125257.jpg
-vcoco_000000435358.jpg
-vcoco_000000449914.jpg
-vcoco_000000366150.jpg
-vcoco_000000326128.jpg
-vcoco_000000419369.jpg
-vcoco_000000526360.jpg
-vcoco_000000378652.jpg
-vcoco_000000093853.jpg
-vcoco_000000419050.jpg
-vcoco_000000487698.jpg
-vcoco_000000356800.jpg
-vcoco_000000025244.jpg
-vcoco_000000474233.jpg
-vcoco_000000570458.jpg
-vcoco_000000341047.jpg
-vcoco_000000422586.jpg
-vcoco_000000573058.jpg
-vcoco_000000405093.jpg
-vcoco_000000510152.jpg
-vcoco_000000043968.jpg
-vcoco_000000216050.jpg
-vcoco_000000499396.jpg
-vcoco_000000067761.jpg
-vcoco_000000227359.jpg
-vcoco_000000506515.jpg
-vcoco_000000502936.jpg
-vcoco_000000020410.jpg
-vcoco_000000282557.jpg
-vcoco_000000492057.jpg
-vcoco_000000241396.jpg
-vcoco_000000285826.jpg
-vcoco_000000580778.jpg
-vcoco_000000183538.jpg
-vcoco_000000359399.jpg
-vcoco_000000405121.jpg
-vcoco_000000176091.jpg
-vcoco_000000401962.jpg
-vcoco_000000291962.jpg
-vcoco_000000048282.jpg
-vcoco_000000525876.jpg
-vcoco_000000355197.jpg
-vcoco_000000489207.jpg
-vcoco_000000536791.jpg
-vcoco_000000290979.jpg
-vcoco_000000047774.jpg
-vcoco_000000191632.jpg
-vcoco_000000355660.jpg
-vcoco_000000541108.jpg
-vcoco_000000470161.jpg
-vcoco_000000455948.jpg
-vcoco_000000486605.jpg
-vcoco_000000509020.jpg
-vcoco_000000226597.jpg
-vcoco_000000038431.jpg
-vcoco_000000017003.jpg
-vcoco_000000264758.jpg
-vcoco_000000250619.jpg
-vcoco_000000540183.jpg
-vcoco_000000360002.jpg
-vcoco_000000192656.jpg
-vcoco_000000462324.jpg
-vcoco_000000559908.jpg
-vcoco_000000409496.jpg
-vcoco_000000193429.jpg
-vcoco_000000136350.jpg
-vcoco_000000089078.jpg
-vcoco_000000499102.jpg
-vcoco_000000497915.jpg
-vcoco_000000486774.jpg
-vcoco_000000276006.jpg
-vcoco_000000078871.jpg
-vcoco_000000458103.jpg
-vcoco_000000014226.jpg
-vcoco_000000332087.jpg
-vcoco_000000195697.jpg
-vcoco_000000280968.jpg
-vcoco_000000563435.jpg
-vcoco_000000491118.jpg
-vcoco_000000341681.jpg
-vcoco_000000465247.jpg
-vcoco_000000433574.jpg
-vcoco_000000082969.jpg
-vcoco_000000131339.jpg
-vcoco_000000330650.jpg
-vcoco_000000363102.jpg
-vcoco_000000573063.jpg
-vcoco_000000320661.jpg
-vcoco_000000053058.jpg
-vcoco_000000579891.jpg
-vcoco_000000327804.jpg
-vcoco_000000525684.jpg
-vcoco_000000157948.jpg
-vcoco_000000531735.jpg
-vcoco_000000549746.jpg
-vcoco_000000378894.jpg
-vcoco_000000096800.jpg
-vcoco_000000068586.jpg
-vcoco_000000564091.jpg
-vcoco_000000010149.jpg
-vcoco_000000357356.jpg
-vcoco_000000008383.jpg
-vcoco_000000562062.jpg
-vcoco_000000318672.jpg
-vcoco_000000285013.jpg
-vcoco_000000486070.jpg
-vcoco_000000420347.jpg
-vcoco_000000246053.jpg
-vcoco_000000510078.jpg
-vcoco_000000270683.jpg
-vcoco_000000412876.jpg
-vcoco_000000204272.jpg
-vcoco_000000441995.jpg
-vcoco_000000404283.jpg
-vcoco_000000467843.jpg
-vcoco_000000529670.jpg
-vcoco_000000575348.jpg
-vcoco_000000382383.jpg
-vcoco_000000308053.jpg
-vcoco_000000303610.jpg
-vcoco_000000035093.jpg
-vcoco_000000029140.jpg
-vcoco_000000575719.jpg
-vcoco_000000515424.jpg
-vcoco_000000110693.jpg
-vcoco_000000559948.jpg
-vcoco_000000345252.jpg
-vcoco_000000032151.jpg
-vcoco_000000157651.jpg
-vcoco_000000085626.jpg
-vcoco_000000314645.jpg
-vcoco_000000326243.jpg
-vcoco_000000259585.jpg
-vcoco_000000063248.jpg
-vcoco_000000353835.jpg
-vcoco_000000291921.jpg
-vcoco_000000079031.jpg
-vcoco_000000181330.jpg
-vcoco_000000546658.jpg
-vcoco_000000137888.jpg
-vcoco_000000333626.jpg
-vcoco_000000452115.jpg
-vcoco_000000315742.jpg
-vcoco_000000411241.jpg
-vcoco_000000246436.jpg
-vcoco_000000280084.jpg
-vcoco_000000404820.jpg
-vcoco_000000110490.jpg
-vcoco_000000422918.jpg
-vcoco_000000020161.jpg
-vcoco_000000163085.jpg
-vcoco_000000515123.jpg
-vcoco_000000519905.jpg
-vcoco_000000534687.jpg
-vcoco_000000508724.jpg
-vcoco_000000546320.jpg
-vcoco_000000475271.jpg
-vcoco_000000456969.jpg
-vcoco_000000334530.jpg
-vcoco_000000448181.jpg
-vcoco_000000258761.jpg
-vcoco_000000571640.jpg
-vcoco_000000238502.jpg
-vcoco_000000365728.jpg
-vcoco_000000421253.jpg
-vcoco_000000207177.jpg
-vcoco_000000450567.jpg
-vcoco_000000386261.jpg
-vcoco_000000261902.jpg
-vcoco_000000036322.jpg
-vcoco_000000230851.jpg
-vcoco_000000417298.jpg
-vcoco_000000400080.jpg
-vcoco_000000038049.jpg
-vcoco_000000288486.jpg
-vcoco_000000475952.jpg
-vcoco_000000258769.jpg
-vcoco_000000158684.jpg
-vcoco_000000120994.jpg
-vcoco_000000134926.jpg
-vcoco_000000522413.jpg
-vcoco_000000575389.jpg
-vcoco_000000317018.jpg
-vcoco_000000503332.jpg
-vcoco_000000343438.jpg
-vcoco_000000006041.jpg
-vcoco_000000440554.jpg
-vcoco_000000109666.jpg
-vcoco_000000514468.jpg
-vcoco_000000381607.jpg
-vcoco_000000357769.jpg
-vcoco_000000576754.jpg
-vcoco_000000519351.jpg
-vcoco_000000296906.jpg
-vcoco_000000508949.jpg
-vcoco_000000515924.jpg
-vcoco_000000516339.jpg
-vcoco_000000564328.jpg
-vcoco_000000169854.jpg
-vcoco_000000457906.jpg
-vcoco_000000045086.jpg
-vcoco_000000387270.jpg
-vcoco_000000095854.jpg
-vcoco_000000228920.jpg
-vcoco_000000324971.jpg
-vcoco_000000505242.jpg
-vcoco_000000006189.jpg
-vcoco_000000562602.jpg
-vcoco_000000449661.jpg
-vcoco_000000069029.jpg
-vcoco_000000511325.jpg
-vcoco_000000501576.jpg
-vcoco_000000560632.jpg
-vcoco_000000514083.jpg
-vcoco_000000022371.jpg
-vcoco_000000258141.jpg
-vcoco_000000489573.jpg
-vcoco_000000541017.jpg
-vcoco_000000565570.jpg
-vcoco_000000503421.jpg
-vcoco_000000556083.jpg
-vcoco_000000450340.jpg
-vcoco_000000462676.jpg
-vcoco_000000520478.jpg
-vcoco_000000226374.jpg
-vcoco_000000436544.jpg
-vcoco_000000227250.jpg
-vcoco_000000482172.jpg
-vcoco_000000502113.jpg
-vcoco_000000346863.jpg
-vcoco_000000305156.jpg
-vcoco_000000292211.jpg
-vcoco_000000368602.jpg
-vcoco_000000457400.jpg
-vcoco_000000013985.jpg
-vcoco_000000248007.jpg
-vcoco_000000475919.jpg
-vcoco_000000087501.jpg
-vcoco_000000056669.jpg
-vcoco_000000510061.jpg
-vcoco_000000417870.jpg
-vcoco_000000353976.jpg
-vcoco_000000036663.jpg
-vcoco_000000302740.jpg
-vcoco_000000321776.jpg
-vcoco_000000011195.jpg
-vcoco_000000489313.jpg
-vcoco_000000106411.jpg
-vcoco_000000445933.jpg
-vcoco_000000138834.jpg
-vcoco_000000567530.jpg
-vcoco_000000342650.jpg
-vcoco_000000109232.jpg
-vcoco_000000318444.jpg
-vcoco_000000414923.jpg
-vcoco_000000185792.jpg
-vcoco_000000259565.jpg
-vcoco_000000140065.jpg
-vcoco_000000305760.jpg
-vcoco_000000561512.jpg
-vcoco_000000491058.jpg
-vcoco_000000236865.jpg
-vcoco_000000233188.jpg
-vcoco_000000172264.jpg
-vcoco_000000531633.jpg
-vcoco_000000541474.jpg
-vcoco_000000558006.jpg
-vcoco_000000460781.jpg
-vcoco_000000299116.jpg
-vcoco_000000419444.jpg
-vcoco_000000563912.jpg
-vcoco_000000062623.jpg
-vcoco_000000416072.jpg
-vcoco_000000111148.jpg
-vcoco_000000371555.jpg
-vcoco_000000313925.jpg
-vcoco_000000084004.jpg
-vcoco_000000183843.jpg
-vcoco_000000579060.jpg
-vcoco_000000129852.jpg
-vcoco_000000509526.jpg
-vcoco_000000484584.jpg
-vcoco_000000190277.jpg
-vcoco_000000400332.jpg
-vcoco_000000133620.jpg
-vcoco_000000239119.jpg
-vcoco_000000516261.jpg
-vcoco_000000323789.jpg
-vcoco_000000310131.jpg
-vcoco_000000504353.jpg
-vcoco_000000217486.jpg
-vcoco_000000439386.jpg
-vcoco_000000558089.jpg
-vcoco_000000441218.jpg
-vcoco_000000050782.jpg
-vcoco_000000395304.jpg
-vcoco_000000276893.jpg
-vcoco_000000279013.jpg
-vcoco_000000565518.jpg
-vcoco_000000579261.jpg
-vcoco_000000364433.jpg
-vcoco_000000024242.jpg
-vcoco_000000332916.jpg
-vcoco_000000443095.jpg
-vcoco_000000497343.jpg
-vcoco_000000400168.jpg
-vcoco_000000073172.jpg
-vcoco_000000445263.jpg
-vcoco_000000090628.jpg
-vcoco_000000341645.jpg
-vcoco_000000308145.jpg
-vcoco_000000133766.jpg
-vcoco_000000549683.jpg
-vcoco_000000060596.jpg
-vcoco_000000059685.jpg
-vcoco_000000039664.jpg
-vcoco_000000076901.jpg
-vcoco_000000290130.jpg
-vcoco_000000354290.jpg
-vcoco_000000572296.jpg
-vcoco_000000197862.jpg
-vcoco_000000381544.jpg
-vcoco_000000400925.jpg
-vcoco_000000047315.jpg
-vcoco_000000069965.jpg
-vcoco_000000158058.jpg
-vcoco_000000238857.jpg
-vcoco_000000435468.jpg
-vcoco_000000074838.jpg
-vcoco_000000505636.jpg
-vcoco_000000494782.jpg
-vcoco_000000016210.jpg
-vcoco_000000357413.jpg
-vcoco_000000432062.jpg
-vcoco_000000390435.jpg
-vcoco_000000072910.jpg
-vcoco_000000325838.jpg
-vcoco_000000483639.jpg
-vcoco_000000331367.jpg
-vcoco_000000374368.jpg
-vcoco_000000025282.jpg
-vcoco_000000334625.jpg
-vcoco_000000413217.jpg
-vcoco_000000221132.jpg
-vcoco_000000333924.jpg
-vcoco_000000076994.jpg
-vcoco_000000074349.jpg
-vcoco_000000284131.jpg
-vcoco_000000389577.jpg
-vcoco_000000323895.jpg
-vcoco_000000028692.jpg
-vcoco_000000230133.jpg
-vcoco_000000130513.jpg
-vcoco_000000285302.jpg
-vcoco_000000293554.jpg
-vcoco_000000034900.jpg
-vcoco_000000485902.jpg
-vcoco_000000443844.jpg
-vcoco_000000115898.jpg
-vcoco_000000377105.jpg
-vcoco_000000282564.jpg
-vcoco_000000413154.jpg
-vcoco_000000264819.jpg
-vcoco_000000395225.jpg
-vcoco_000000456566.jpg
-vcoco_000000048044.jpg
-vcoco_000000420167.jpg
-vcoco_000000576625.jpg
-vcoco_000000579760.jpg
-vcoco_000000399294.jpg
-vcoco_000000034356.jpg
-vcoco_000000358617.jpg
-vcoco_000000492968.jpg
-vcoco_000000325242.jpg
-vcoco_000000109537.jpg
-vcoco_000000459585.jpg
-vcoco_000000281008.jpg
-vcoco_000000029045.jpg
-vcoco_000000068277.jpg
-vcoco_000000444927.jpg
-vcoco_000000050638.jpg
-vcoco_000000532295.jpg
-vcoco_000000427941.jpg
-vcoco_000000452471.jpg
-vcoco_000000483066.jpg
-vcoco_000000501381.jpg
-vcoco_000000280761.jpg
-vcoco_000000403349.jpg
-vcoco_000000314154.jpg
-vcoco_000000456807.jpg
-vcoco_000000174176.jpg
-vcoco_000000441608.jpg
-vcoco_000000071124.jpg
-vcoco_000000400742.jpg
-vcoco_000000282943.jpg
-vcoco_000000445908.jpg
-vcoco_000000412879.jpg
-vcoco_000000386363.jpg
-vcoco_000000474026.jpg
-vcoco_000000047548.jpg
-vcoco_000000468299.jpg
-vcoco_000000398941.jpg
-vcoco_000000503976.jpg
-vcoco_000000169648.jpg
-vcoco_000000369936.jpg
-vcoco_000000433170.jpg
-vcoco_000000329498.jpg
-vcoco_000000372604.jpg
-vcoco_000000278462.jpg
-vcoco_000000093075.jpg
-vcoco_000000312985.jpg
-vcoco_000000358525.jpg
-vcoco_000000064310.jpg
-vcoco_000000280908.jpg
-vcoco_000000536214.jpg
-vcoco_000000578572.jpg
-vcoco_000000380330.jpg
-vcoco_000000403680.jpg
-vcoco_000000450687.jpg
-vcoco_000000436984.jpg
-vcoco_000000220457.jpg
-vcoco_000000104023.jpg
-vcoco_000000334813.jpg
-vcoco_000000494860.jpg
-vcoco_000000418384.jpg
-vcoco_000000064462.jpg
-vcoco_000000314204.jpg
-vcoco_000000431364.jpg
-vcoco_000000108425.jpg
-vcoco_000000461644.jpg
-vcoco_000000012938.jpg
-vcoco_000000066676.jpg
-vcoco_000000560969.jpg
-vcoco_000000502202.jpg
-vcoco_000000282733.jpg
-vcoco_000000480408.jpg
-vcoco_000000345139.jpg
-vcoco_000000400044.jpg
-vcoco_000000228135.jpg
-vcoco_000000440347.jpg
-vcoco_000000404373.jpg
-vcoco_000000476139.jpg
-vcoco_000000443204.jpg
-vcoco_000000437594.jpg
-vcoco_000000415109.jpg
-vcoco_000000443681.jpg
-vcoco_000000564304.jpg
-vcoco_000000349709.jpg
-vcoco_000000323153.jpg
-vcoco_000000385323.jpg
-vcoco_000000203631.jpg
-vcoco_000000477066.jpg
-vcoco_000000264179.jpg
-vcoco_000000535174.jpg
-vcoco_000000542723.jpg
-vcoco_000000133576.jpg
-vcoco_000000203809.jpg
-vcoco_000000353989.jpg
-vcoco_000000121083.jpg
-vcoco_000000308399.jpg
-vcoco_000000034428.jpg
-vcoco_000000422211.jpg
-vcoco_000000487898.jpg
-vcoco_000000444308.jpg
-vcoco_000000566518.jpg
-vcoco_000000426469.jpg
-vcoco_000000272095.jpg
-vcoco_000000091336.jpg
-vcoco_000000179526.jpg
-vcoco_000000419212.jpg
-vcoco_000000318179.jpg
-vcoco_000000446285.jpg
-vcoco_000000467875.jpg
-vcoco_000000204935.jpg
-vcoco_000000456345.jpg
-vcoco_000000554711.jpg
-vcoco_000000565203.jpg
-vcoco_000000313361.jpg
-vcoco_000000128113.jpg
-vcoco_000000408481.jpg
-vcoco_000000398798.jpg
-vcoco_000000144610.jpg
-vcoco_000000532449.jpg
-vcoco_000000267837.jpg
-vcoco_000000103722.jpg
-vcoco_000000476398.jpg
-vcoco_000000412681.jpg
-vcoco_000000447728.jpg
-vcoco_000000299254.jpg
-vcoco_000000361171.jpg
-vcoco_000000187001.jpg
-vcoco_000000309284.jpg
-vcoco_000000528966.jpg
-vcoco_000000231714.jpg
-vcoco_000000580847.jpg
-vcoco_000000475159.jpg
-vcoco_000000492535.jpg
-vcoco_000000054329.jpg
-vcoco_000000034825.jpg
-vcoco_000000266866.jpg
-vcoco_000000266715.jpg
-vcoco_000000578119.jpg
-vcoco_000000176312.jpg
-vcoco_000000202853.jpg
-vcoco_000000115584.jpg
-vcoco_000000123974.jpg
-vcoco_000000278973.jpg
-vcoco_000000461715.jpg
-vcoco_000000073333.jpg
-vcoco_000000114389.jpg
-vcoco_000000160828.jpg
-vcoco_000000275117.jpg
-vcoco_000000228505.jpg
-vcoco_000000031521.jpg
-vcoco_000000420156.jpg
-vcoco_000000450894.jpg
-vcoco_000000107430.jpg
-vcoco_000000467654.jpg
-vcoco_000000095916.jpg
-vcoco_000000561849.jpg
-vcoco_000000385154.jpg
-vcoco_000000409367.jpg
-vcoco_000000434637.jpg
-vcoco_000000535552.jpg
-vcoco_000000512455.jpg
-vcoco_000000331083.jpg
-vcoco_000000516318.jpg
-vcoco_000000288984.jpg
-vcoco_000000451751.jpg
-vcoco_000000295114.jpg
-vcoco_000000180584.jpg
-vcoco_000000494936.jpg
-vcoco_000000551175.jpg
-vcoco_000000536087.jpg
-vcoco_000000460997.jpg
-vcoco_000000561437.jpg
-vcoco_000000329307.jpg
-vcoco_000000035979.jpg
-vcoco_000000442695.jpg
-vcoco_000000307186.jpg
-vcoco_000000468612.jpg
-vcoco_000000426453.jpg
-vcoco_000000403109.jpg
-vcoco_000000521094.jpg
-vcoco_000000378499.jpg
-vcoco_000000343159.jpg
-vcoco_000000053121.jpg
-vcoco_000000008923.jpg
-vcoco_000000558454.jpg
-vcoco_000000402109.jpg
-vcoco_000000262642.jpg
-vcoco_000000570263.jpg
-vcoco_000000577980.jpg
-vcoco_000000500944.jpg
-vcoco_000000329016.jpg
-vcoco_000000517807.jpg
-vcoco_000000467113.jpg
-vcoco_000000498733.jpg
-vcoco_000000007333.jpg
-vcoco_000000308509.jpg
-vcoco_000000471601.jpg
-vcoco_000000109042.jpg
-vcoco_000000018250.jpg
-vcoco_000000427762.jpg
-vcoco_000000354976.jpg
-vcoco_000000057767.jpg
-vcoco_000000410066.jpg
-vcoco_000000195594.jpg
-vcoco_000000580972.jpg
-vcoco_000000438617.jpg
-vcoco_000000326420.jpg
-vcoco_000000349354.jpg
-vcoco_000000557396.jpg
-vcoco_000000492271.jpg
-vcoco_000000510138.jpg
-vcoco_000000496768.jpg
-vcoco_000000442097.jpg
-vcoco_000000324605.jpg
-vcoco_000000551439.jpg
-vcoco_000000314193.jpg
-vcoco_000000548224.jpg
-vcoco_000000526955.jpg
-vcoco_000000442094.jpg
-vcoco_000000517101.jpg
-vcoco_000000563302.jpg
-vcoco_000000497719.jpg
-vcoco_000000418074.jpg
-vcoco_000000431566.jpg
-vcoco_000000417911.jpg
-vcoco_000000166478.jpg
-vcoco_000000397777.jpg
-vcoco_000000535706.jpg
-vcoco_000000309120.jpg
-vcoco_000000396688.jpg
-vcoco_000000536607.jpg
-vcoco_000000321132.jpg
-vcoco_000000095211.jpg
-vcoco_000000266847.jpg
-vcoco_000000155873.jpg
-vcoco_000000080185.jpg
-vcoco_000000242612.jpg
-vcoco_000000555217.jpg
-vcoco_000000459258.jpg
-vcoco_000000177015.jpg
-vcoco_000000109503.jpg
-vcoco_000000390689.jpg
-vcoco_000000132430.jpg
-vcoco_000000431342.jpg
-vcoco_000000572749.jpg
-vcoco_000000557830.jpg
-vcoco_000000450709.jpg
-vcoco_000000310035.jpg
-vcoco_000000531696.jpg
-vcoco_000000334723.jpg
-vcoco_000000517941.jpg
-vcoco_000000467246.jpg
-vcoco_000000286953.jpg
-vcoco_000000550787.jpg
-vcoco_000000211604.jpg
-vcoco_000000495485.jpg
-vcoco_000000227370.jpg
-vcoco_000000477172.jpg
-vcoco_000000159213.jpg
-vcoco_000000376509.jpg
-vcoco_000000401310.jpg
-vcoco_000000480936.jpg
-vcoco_000000428254.jpg
-vcoco_000000316298.jpg
-vcoco_000000361384.jpg
-vcoco_000000451043.jpg
-vcoco_000000476738.jpg
-vcoco_000000504170.jpg
-vcoco_000000392443.jpg
-vcoco_000000053490.jpg
-vcoco_000000329841.jpg
-vcoco_000000358307.jpg
-vcoco_000000418907.jpg
-vcoco_000000312078.jpg
-vcoco_000000043872.jpg
-vcoco_000000550453.jpg
-vcoco_000000549937.jpg
-vcoco_000000247366.jpg
-vcoco_000000469198.jpg
-vcoco_000000379578.jpg
-vcoco_000000415885.jpg
-vcoco_000000111756.jpg
-vcoco_000000421309.jpg
-vcoco_000000373318.jpg
-vcoco_000000342770.jpg
-vcoco_000000379230.jpg
-vcoco_000000103705.jpg
-vcoco_000000160471.jpg
-vcoco_000000106575.jpg
-vcoco_000000374010.jpg
-vcoco_000000198426.jpg
-vcoco_000000321495.jpg
-vcoco_000000422517.jpg
-vcoco_000000180460.jpg
-vcoco_000000337439.jpg
-vcoco_000000441795.jpg
-vcoco_000000321907.jpg
-vcoco_000000460039.jpg
-vcoco_000000437592.jpg
-vcoco_000000084155.jpg
-vcoco_000000528517.jpg
-vcoco_000000412286.jpg
-vcoco_000000472394.jpg
-vcoco_000000132617.jpg
-vcoco_000000293353.jpg
-vcoco_000000554595.jpg
-vcoco_000000315200.jpg
-vcoco_000000498263.jpg
-vcoco_000000236141.jpg
-vcoco_000000321432.jpg
-vcoco_000000388468.jpg
-vcoco_000000487718.jpg
-vcoco_000000530543.jpg
-vcoco_000000405223.jpg
-vcoco_000000154362.jpg
-vcoco_000000417416.jpg
-vcoco_000000239204.jpg
-vcoco_000000570567.jpg
-vcoco_000000322362.jpg
-vcoco_000000160735.jpg
-vcoco_000000248831.jpg
-vcoco_000000518052.jpg
-vcoco_000000356505.jpg
-vcoco_000000208263.jpg
-vcoco_000000560704.jpg
-vcoco_000000387724.jpg
-vcoco_000000533159.jpg
-vcoco_000000399284.jpg
-vcoco_000000082936.jpg
-vcoco_000000154369.jpg
-vcoco_000000559209.jpg
-vcoco_000000508605.jpg
-vcoco_000000299723.jpg
-vcoco_000000075527.jpg
-vcoco_000000431480.jpg
-vcoco_000000570474.jpg
-vcoco_000000491449.jpg
-vcoco_000000398463.jpg
-vcoco_000000280083.jpg
-vcoco_000000343937.jpg
-vcoco_000000569758.jpg
-vcoco_000000265550.jpg
-vcoco_000000554059.jpg
-vcoco_000000397190.jpg
-vcoco_000000533742.jpg
-vcoco_000000569872.jpg
-vcoco_000000428288.jpg
-vcoco_000000077754.jpg
-vcoco_000000552188.jpg
-vcoco_000000573967.jpg
-vcoco_000000447330.jpg
-vcoco_000000513039.jpg
-vcoco_000000342929.jpg
-vcoco_000000396693.jpg
-vcoco_000000499027.jpg
-vcoco_000000312504.jpg
-vcoco_000000515785.jpg
-vcoco_000000119248.jpg
-vcoco_000000111910.jpg
-vcoco_000000053589.jpg
-vcoco_000000352399.jpg
-vcoco_000000260651.jpg
-vcoco_000000524047.jpg
-vcoco_000000384780.jpg
-vcoco_000000184227.jpg
-vcoco_000000549427.jpg
-vcoco_000000522054.jpg
-vcoco_000000338802.jpg
-vcoco_000000409198.jpg
-vcoco_000000158996.jpg
-vcoco_000000313220.jpg
-vcoco_000000396821.jpg
-vcoco_000000551763.jpg
-vcoco_000000039778.jpg
-vcoco_000000471762.jpg
-vcoco_000000408190.jpg
-vcoco_000000461884.jpg
-vcoco_000000208657.jpg
-vcoco_000000412296.jpg
-vcoco_000000513861.jpg
-vcoco_000000353740.jpg
-vcoco_000000551701.jpg
-vcoco_000000296459.jpg
-vcoco_000000276491.jpg
-vcoco_000000301443.jpg
-vcoco_000000399873.jpg
-vcoco_000000269015.jpg
-vcoco_000000551676.jpg
-vcoco_000000109937.jpg
-vcoco_000000553965.jpg
-vcoco_000000390315.jpg
-vcoco_000000329134.jpg
-vcoco_000000565877.jpg
-vcoco_000000053431.jpg
-vcoco_000000256475.jpg
-vcoco_000000270609.jpg
-vcoco_000000419262.jpg
-vcoco_000000487482.jpg
-vcoco_000000211520.jpg
-vcoco_000000528729.jpg
-vcoco_000000305004.jpg
-vcoco_000000453529.jpg
-vcoco_000000461898.jpg
-vcoco_000000499268.jpg
-vcoco_000000556892.jpg
-vcoco_000000536879.jpg
-vcoco_000000284831.jpg
-vcoco_000000338910.jpg
-vcoco_000000153797.jpg
-vcoco_000000450559.jpg
-vcoco_000000078436.jpg
-vcoco_000000546717.jpg
-vcoco_000000342174.jpg
-vcoco_000000047801.jpg
-vcoco_000000360297.jpg
-vcoco_000000417259.jpg
-vcoco_000000186711.jpg
-vcoco_000000517967.jpg
-vcoco_000000452964.jpg
-vcoco_000000036086.jpg
-vcoco_000000449603.jpg
-vcoco_000000315037.jpg
-vcoco_000000289572.jpg
-vcoco_000000446358.jpg
-vcoco_000000331858.jpg
-vcoco_000000132114.jpg
-vcoco_000000561223.jpg
-vcoco_000000120416.jpg
-vcoco_000000353968.jpg
-vcoco_000000511384.jpg
-vcoco_000000546295.jpg
-vcoco_000000547246.jpg
-vcoco_000000054516.jpg
-vcoco_000000343514.jpg
-vcoco_000000485027.jpg
-vcoco_000000573453.jpg
-vcoco_000000046893.jpg
-vcoco_000000330478.jpg
-vcoco_000000527002.jpg
-vcoco_000000017559.jpg
-vcoco_000000407441.jpg
-vcoco_000000365701.jpg
-vcoco_000000274870.jpg
-vcoco_000000311902.jpg
-vcoco_000000101065.jpg
-vcoco_000000498509.jpg
-vcoco_000000185479.jpg
-vcoco_000000121827.jpg
-vcoco_000000082666.jpg
-vcoco_000000456254.jpg
-vcoco_000000522758.jpg
-vcoco_000000084397.jpg
-vcoco_000000480747.jpg
-vcoco_000000431859.jpg
-vcoco_000000371497.jpg
-vcoco_000000431116.jpg
-vcoco_000000249046.jpg
-vcoco_000000316143.jpg
-vcoco_000000416188.jpg
-vcoco_000000260261.jpg
-vcoco_000000199381.jpg
-vcoco_000000465199.jpg
-vcoco_000000261569.jpg
-vcoco_000000524118.jpg
-vcoco_000000104999.jpg
-vcoco_000000189839.jpg
-vcoco_000000523997.jpg
-vcoco_000000554541.jpg
-vcoco_000000535100.jpg
-vcoco_000000529455.jpg
-vcoco_000000581062.jpg
-vcoco_000000420487.jpg
-vcoco_000000476827.jpg
-vcoco_000000373500.jpg
-vcoco_000000255495.jpg
-vcoco_000000050553.jpg
-vcoco_000000413044.jpg
-vcoco_000000384755.jpg
-vcoco_000000500005.jpg
-vcoco_000000401797.jpg
-vcoco_000000406294.jpg
-vcoco_000000274715.jpg
-vcoco_000000160001.jpg
-vcoco_000000446473.jpg
-vcoco_000000545525.jpg
-vcoco_000000551737.jpg
-vcoco_000000004386.jpg
-vcoco_000000045367.jpg
-vcoco_000000114458.jpg
-vcoco_000000249325.jpg
-vcoco_000000467257.jpg
-vcoco_000000504224.jpg
-vcoco_000000295154.jpg
-vcoco_000000516516.jpg
-vcoco_000000223214.jpg
-vcoco_000000112949.jpg
-vcoco_000000226660.jpg
-vcoco_000000519852.jpg
-vcoco_000000051181.jpg
-vcoco_000000170118.jpg
-vcoco_000000468162.jpg
-vcoco_000000565957.jpg
-vcoco_000000518370.jpg
-vcoco_000000371633.jpg
-vcoco_000000382307.jpg
-vcoco_000000533628.jpg
-vcoco_000000265810.jpg
-vcoco_000000454359.jpg
-vcoco_000000288576.jpg
-vcoco_000000276151.jpg
-vcoco_000000572326.jpg
-vcoco_000000459304.jpg
-vcoco_000000357916.jpg
-vcoco_000000173375.jpg
-vcoco_000000026132.jpg
-vcoco_000000450543.jpg
-vcoco_000000261318.jpg
-vcoco_000000458637.jpg
-vcoco_000000266160.jpg
-vcoco_000000419816.jpg
-vcoco_000000531036.jpg
-vcoco_000000537743.jpg
-vcoco_000000226562.jpg
-vcoco_000000437540.jpg
-vcoco_000000129379.jpg
-vcoco_000000258869.jpg
-vcoco_000000409523.jpg
-vcoco_000000494900.jpg
-vcoco_000000335650.jpg
-vcoco_000000511324.jpg
-vcoco_000000083778.jpg
-vcoco_000000054091.jpg
-vcoco_000000171016.jpg
-vcoco_000000554727.jpg
-vcoco_000000422545.jpg
-vcoco_000000132510.jpg
-vcoco_000000054007.jpg
-vcoco_000000562850.jpg
-vcoco_000000505234.jpg
-vcoco_000000208629.jpg
-vcoco_000000521943.jpg
-vcoco_000000278801.jpg
-vcoco_000000175642.jpg
-vcoco_000000016285.jpg
-vcoco_000000262116.jpg
-vcoco_000000332582.jpg
-vcoco_000000549462.jpg
-vcoco_000000220917.jpg
-vcoco_000000553285.jpg
-vcoco_000000240028.jpg
-vcoco_000000524623.jpg
-vcoco_000000517468.jpg
-vcoco_000000043555.jpg
-vcoco_000000107148.jpg
-vcoco_000000415243.jpg
-vcoco_000000555582.jpg
-vcoco_000000147595.jpg
-vcoco_000000497244.jpg
-vcoco_000000117691.jpg
-vcoco_000000381856.jpg
-vcoco_000000576463.jpg
-vcoco_000000250309.jpg
-vcoco_000000510864.jpg
-vcoco_000000269098.jpg
-vcoco_000000483089.jpg
-vcoco_000000490847.jpg
-vcoco_000000574829.jpg
-vcoco_000000085154.jpg
-vcoco_000000498765.jpg
-vcoco_000000431693.jpg
-vcoco_000000408288.jpg
-vcoco_000000000693.jpg
-vcoco_000000330205.jpg
-vcoco_000000097596.jpg
-vcoco_000000316189.jpg
-vcoco_000000462381.jpg
-vcoco_000000565233.jpg
-vcoco_000000536241.jpg
-vcoco_000000407987.jpg
-vcoco_000000436391.jpg
-vcoco_000000298380.jpg
-vcoco_000000534048.jpg
-vcoco_000000345751.jpg
-vcoco_000000395576.jpg
-vcoco_000000453037.jpg
-vcoco_000000575664.jpg
-vcoco_000000535685.jpg
-vcoco_000000016817.jpg
-vcoco_000000333629.jpg
-vcoco_000000397705.jpg
-vcoco_000000095201.jpg
-vcoco_000000376531.jpg
-vcoco_000000578449.jpg
-vcoco_000000097270.jpg
-vcoco_000000143107.jpg
-vcoco_000000161190.jpg
-vcoco_000000185945.jpg
-vcoco_000000491665.jpg
-vcoco_000000468966.jpg
-vcoco_000000177807.jpg
-vcoco_000000336484.jpg
-vcoco_000000515792.jpg
-vcoco_000000480883.jpg
-vcoco_000000544059.jpg
-vcoco_000000483213.jpg
-vcoco_000000232451.jpg
-vcoco_000000033643.jpg
-vcoco_000000426376.jpg
-vcoco_000000025024.jpg
-vcoco_000000399605.jpg
-vcoco_000000223740.jpg
-vcoco_000000263586.jpg
-vcoco_000000311620.jpg
-vcoco_000000140388.jpg
-vcoco_000000053990.jpg
-vcoco_000000410272.jpg
-vcoco_000000527427.jpg
-vcoco_000000063525.jpg
-vcoco_000000570471.jpg
-vcoco_000000267443.jpg
-vcoco_000000379488.jpg
-vcoco_000000008309.jpg
-vcoco_000000241373.jpg
-vcoco_000000540614.jpg
-vcoco_000000056455.jpg
-vcoco_000000158582.jpg
-vcoco_000000004498.jpg
-vcoco_000000076893.jpg
-vcoco_000000319765.jpg
-vcoco_000000563299.jpg
-vcoco_000000533770.jpg
-vcoco_000000275919.jpg
-vcoco_000000502935.jpg
-vcoco_000000276381.jpg
-vcoco_000000358884.jpg
-vcoco_000000346577.jpg
-vcoco_000000331883.jpg
-vcoco_000000549754.jpg
-vcoco_000000310606.jpg
-vcoco_000000151075.jpg
-vcoco_000000418185.jpg
-vcoco_000000328337.jpg
-vcoco_000000117197.jpg
-vcoco_000000152564.jpg
-vcoco_000000502776.jpg
-vcoco_000000517636.jpg
-vcoco_000000182840.jpg
-vcoco_000000471756.jpg
-vcoco_000000332990.jpg
-vcoco_000000076992.jpg
-vcoco_000000487843.jpg
-vcoco_000000576652.jpg
-vcoco_000000534412.jpg
-vcoco_000000366379.jpg
-vcoco_000000002758.jpg
-vcoco_000000123851.jpg
-vcoco_000000467752.jpg
-vcoco_000000074832.jpg
-vcoco_000000383454.jpg
-vcoco_000000440813.jpg
-vcoco_000000440153.jpg
-vcoco_000000025096.jpg
-vcoco_000000094046.jpg
-vcoco_000000038886.jpg
-vcoco_000000545226.jpg
-vcoco_000000537206.jpg
-vcoco_000000419249.jpg
-vcoco_000000456302.jpg
-vcoco_000000549115.jpg
-vcoco_000000563575.jpg
-vcoco_000000581040.jpg
-vcoco_000000454916.jpg
-vcoco_000000308744.jpg
-vcoco_000000488980.jpg
-vcoco_000000235479.jpg
-vcoco_000000322473.jpg
-vcoco_000000291209.jpg
-vcoco_000000262235.jpg
-vcoco_000000482002.jpg
-vcoco_000000554674.jpg
-vcoco_000000108301.jpg
-vcoco_000000281040.jpg
-vcoco_000000423113.jpg
-vcoco_000000207634.jpg
-vcoco_000000292482.jpg
-vcoco_000000141920.jpg
-vcoco_000000520204.jpg
-vcoco_000000548834.jpg
-vcoco_000000490171.jpg
-vcoco_000000271759.jpg
-vcoco_000000490280.jpg
-vcoco_000000552488.jpg
-vcoco_000000141557.jpg
-vcoco_000000407646.jpg
-vcoco_000000351595.jpg
-vcoco_000000544857.jpg
-vcoco_000000361140.jpg
-vcoco_000000282225.jpg
-vcoco_000000527868.jpg
-vcoco_000000078803.jpg
-vcoco_000000375021.jpg
-vcoco_000000340658.jpg
-vcoco_000000088576.jpg
-vcoco_000000426275.jpg
-vcoco_000000213090.jpg
-vcoco_000000110769.jpg
-vcoco_000000383289.jpg
-vcoco_000000079619.jpg
-vcoco_000000463055.jpg
-vcoco_000000578993.jpg
-vcoco_000000536028.jpg
-vcoco_000000381492.jpg
-vcoco_000000248224.jpg
-vcoco_000000393874.jpg
-vcoco_000000418929.jpg
-vcoco_000000146742.jpg
-vcoco_000000515219.jpg
-vcoco_000000083058.jpg
-vcoco_000000291752.jpg
-vcoco_000000386880.jpg
-vcoco_000000482819.jpg
-vcoco_000000051054.jpg
-vcoco_000000120061.jpg
-vcoco_000000030958.jpg
-vcoco_000000523201.jpg
-vcoco_000000030534.jpg
-vcoco_000000203416.jpg
-vcoco_000000424521.jpg
-vcoco_000000462114.jpg
-vcoco_000000527092.jpg
-vcoco_000000503808.jpg
-vcoco_000000140860.jpg
-vcoco_000000372464.jpg
-vcoco_000000335859.jpg
-vcoco_000000258399.jpg
-vcoco_000000299773.jpg
-vcoco_000000480437.jpg
-vcoco_000000547457.jpg
-vcoco_000000420298.jpg
-vcoco_000000044170.jpg
-vcoco_000000290234.jpg
-vcoco_000000490515.jpg
-vcoco_000000439756.jpg
-vcoco_000000084113.jpg
-vcoco_000000018193.jpg
-vcoco_000000381667.jpg
-vcoco_000000272064.jpg
-vcoco_000000455227.jpg
-vcoco_000000122586.jpg
-vcoco_000000360818.jpg
-vcoco_000000575601.jpg
-vcoco_000000459153.jpg
-vcoco_000000171788.jpg
-vcoco_000000447770.jpg
-vcoco_000000008803.jpg
-vcoco_000000481415.jpg
-vcoco_000000568155.jpg
-vcoco_000000402410.jpg
-vcoco_000000137140.jpg
-vcoco_000000035672.jpg
-vcoco_000000521209.jpg
-vcoco_000000050518.jpg
-vcoco_000000345665.jpg
-vcoco_000000376817.jpg
-vcoco_000000537345.jpg
-vcoco_000000450940.jpg
-vcoco_000000454478.jpg
-vcoco_000000368219.jpg
-vcoco_000000331604.jpg
-vcoco_000000295837.jpg
-vcoco_000000580315.jpg
-vcoco_000000457889.jpg
-vcoco_000000342495.jpg
-vcoco_000000451345.jpg
-vcoco_000000191226.jpg
-vcoco_000000460916.jpg
-vcoco_000000291498.jpg
-vcoco_000000388153.jpg
-vcoco_000000438186.jpg
-vcoco_000000485985.jpg
-vcoco_000000075179.jpg
-vcoco_000000576792.jpg
-vcoco_000000298331.jpg
-vcoco_000000549216.jpg
-vcoco_000000002278.jpg
-vcoco_000000560757.jpg
-vcoco_000000234031.jpg
-vcoco_000000068525.jpg
-vcoco_000000519209.jpg
-vcoco_000000184919.jpg
-vcoco_000000324969.jpg
-vcoco_000000401829.jpg
-vcoco_000000504287.jpg
-vcoco_000000478433.jpg
-vcoco_000000576305.jpg
-vcoco_000000493728.jpg
-vcoco_000000462065.jpg
-vcoco_000000388510.jpg
-vcoco_000000114404.jpg
-vcoco_000000467580.jpg
-vcoco_000000578788.jpg
-vcoco_000000465323.jpg
-vcoco_000000294410.jpg
-vcoco_000000290320.jpg
-vcoco_000000506061.jpg
-vcoco_000000168775.jpg
-vcoco_000000398858.jpg
-vcoco_000000450737.jpg
-vcoco_000000412621.jpg
-vcoco_000000413970.jpg
-vcoco_000000278359.jpg
-vcoco_000000239769.jpg
-vcoco_000000499200.jpg
-vcoco_000000258330.jpg
-vcoco_000000478723.jpg
-vcoco_000000438894.jpg
-vcoco_000000537864.jpg
-vcoco_000000075655.jpg
-vcoco_000000258061.jpg
-vcoco_000000442746.jpg
-vcoco_000000099964.jpg
-vcoco_000000367776.jpg
-vcoco_000000579056.jpg
-vcoco_000000203479.jpg
-vcoco_000000408219.jpg
-vcoco_000000353707.jpg
-vcoco_000000431715.jpg
-vcoco_000000357831.jpg
-vcoco_000000143154.jpg
-vcoco_000000309314.jpg
-vcoco_000000498807.jpg
-vcoco_000000484978.jpg
-vcoco_000000341113.jpg
-vcoco_000000118104.jpg
-vcoco_000000516856.jpg
-vcoco_000000409722.jpg
-vcoco_000000048270.jpg
-vcoco_000000175757.jpg
-vcoco_000000447124.jpg
-vcoco_000000551024.jpg
-vcoco_000000365687.jpg
-vcoco_000000310998.jpg
-vcoco_000000295716.jpg
-vcoco_000000368521.jpg
-vcoco_000000160345.jpg
-vcoco_000000570225.jpg
-vcoco_000000365851.jpg
-vcoco_000000439773.jpg
-vcoco_000000467068.jpg
-vcoco_000000548546.jpg
-vcoco_000000081379.jpg
-vcoco_000000395899.jpg
-vcoco_000000312552.jpg
-vcoco_000000476258.jpg
-vcoco_000000415889.jpg
-vcoco_000000268159.jpg
-vcoco_000000405762.jpg
-vcoco_000000313166.jpg
-vcoco_000000142620.jpg
-vcoco_000000248591.jpg
-vcoco_000000244768.jpg
-vcoco_000000322177.jpg
-vcoco_000000469896.jpg
-vcoco_000000247206.jpg
-vcoco_000000389273.jpg
-vcoco_000000505792.jpg
-vcoco_000000158747.jpg
-vcoco_000000487112.jpg
-vcoco_000000541209.jpg
-vcoco_000000278867.jpg
-vcoco_000000170779.jpg
-vcoco_000000404059.jpg
-vcoco_000000473206.jpg
-vcoco_000000509459.jpg
-vcoco_000000240147.jpg
-vcoco_000000043625.jpg
-vcoco_000000042834.jpg
-vcoco_000000404517.jpg
-vcoco_000000077003.jpg
-vcoco_000000397205.jpg
-vcoco_000000338501.jpg
-vcoco_000000031106.jpg
-vcoco_000000146190.jpg
-vcoco_000000409058.jpg
-vcoco_000000432239.jpg
-vcoco_000000520873.jpg
-vcoco_000000408735.jpg
-vcoco_000000574986.jpg
-vcoco_000000410772.jpg
-vcoco_000000464200.jpg
-vcoco_000000574356.jpg
-vcoco_000000040813.jpg
-vcoco_000000497265.jpg
-vcoco_000000247469.jpg
-vcoco_000000118612.jpg
-vcoco_000000492545.jpg
-vcoco_000000330186.jpg
-vcoco_000000568502.jpg
-vcoco_000000572544.jpg
-vcoco_000000263957.jpg
-vcoco_000000304252.jpg
-vcoco_000000008594.jpg
-vcoco_000000105079.jpg
-vcoco_000000029191.jpg
-vcoco_000000027482.jpg
-vcoco_000000445074.jpg
-vcoco_000000564240.jpg
-vcoco_000000065982.jpg
-vcoco_000000510254.jpg
-vcoco_000000290221.jpg
-vcoco_000000264222.jpg
-vcoco_000000055221.jpg
-vcoco_000000330699.jpg
-vcoco_000000406013.jpg
-vcoco_000000068166.jpg
-vcoco_000000290602.jpg
-vcoco_000000474423.jpg
-vcoco_000000525899.jpg
-vcoco_000000433454.jpg
-vcoco_000000393284.jpg
-vcoco_000000475396.jpg
-vcoco_000000571450.jpg
-vcoco_000000325991.jpg
-vcoco_000000547080.jpg
-vcoco_000000206235.jpg
-vcoco_000000350019.jpg
-vcoco_000000564915.jpg
-vcoco_000000156497.jpg
-vcoco_000000129758.jpg
-vcoco_000000413489.jpg
-vcoco_000000187244.jpg
-vcoco_000000134907.jpg
-vcoco_000000572965.jpg
-vcoco_000000501527.jpg
-vcoco_000000493483.jpg
-vcoco_000000566536.jpg
-vcoco_000000405648.jpg
-vcoco_000000484714.jpg
-vcoco_000000067269.jpg
-vcoco_000000336602.jpg
-vcoco_000000113893.jpg
-vcoco_000000325885.jpg
-vcoco_000000519320.jpg
-vcoco_000000011091.jpg
-vcoco_000000476709.jpg
-vcoco_000000333433.jpg
-vcoco_000000106666.jpg
-vcoco_000000525226.jpg
-vcoco_000000304519.jpg
-vcoco_000000152530.jpg
-vcoco_000000293577.jpg
-vcoco_000000298689.jpg
-vcoco_000000276057.jpg
-vcoco_000000410510.jpg
-vcoco_000000247421.jpg
-vcoco_000000381253.jpg
-vcoco_000000316085.jpg
-vcoco_000000508288.jpg
-vcoco_000000448837.jpg
-vcoco_000000444142.jpg
-vcoco_000000314147.jpg
-vcoco_000000369961.jpg
-vcoco_000000282209.jpg
-vcoco_000000097662.jpg
-vcoco_000000077296.jpg
-vcoco_000000260190.jpg
-vcoco_000000454282.jpg
-vcoco_000000566448.jpg
-vcoco_000000510033.jpg
-vcoco_000000566173.jpg
-vcoco_000000548361.jpg
-vcoco_000000485155.jpg
-vcoco_000000451099.jpg
-vcoco_000000222346.jpg
-vcoco_000000446705.jpg
-vcoco_000000506377.jpg
-vcoco_000000079853.jpg
-vcoco_000000513524.jpg
-vcoco_000000368041.jpg
-vcoco_000000124387.jpg
-vcoco_000000369153.jpg
-vcoco_000000041875.jpg
-vcoco_000000309744.jpg
-vcoco_000000231991.jpg
-vcoco_000000541174.jpg
-vcoco_000000470545.jpg
-vcoco_000000317049.jpg
-vcoco_000000461883.jpg
-vcoco_000000406917.jpg
-vcoco_000000552947.jpg
-vcoco_000000272058.jpg
-vcoco_000000350231.jpg
-vcoco_000000465333.jpg
-vcoco_000000505814.jpg
-vcoco_000000147375.jpg
-vcoco_000000493192.jpg
-vcoco_000000275685.jpg
-vcoco_000000248034.jpg
-vcoco_000000416549.jpg
-vcoco_000000126073.jpg
-vcoco_000000501652.jpg
-vcoco_000000323067.jpg
-vcoco_000000015597.jpg
-vcoco_000000510866.jpg
-vcoco_000000461443.jpg
-vcoco_000000567780.jpg
-vcoco_000000497674.jpg
-vcoco_000000321824.jpg
-vcoco_000000572725.jpg
-vcoco_000000298065.jpg
-vcoco_000000354145.jpg
-vcoco_000000380909.jpg
-vcoco_000000449865.jpg
-vcoco_000000136664.jpg
-vcoco_000000542163.jpg
-vcoco_000000135585.jpg
-vcoco_000000454509.jpg
-vcoco_000000535536.jpg
-vcoco_000000509867.jpg
-vcoco_000000404613.jpg
-vcoco_000000308967.jpg
-vcoco_000000331907.jpg
-vcoco_000000569322.jpg
-vcoco_000000519405.jpg
-vcoco_000000447762.jpg
-vcoco_000000092747.jpg
-vcoco_000000250249.jpg
-vcoco_000000519635.jpg
-vcoco_000000487876.jpg
-vcoco_000000570268.jpg
-vcoco_000000409468.jpg
-vcoco_000000468570.jpg
-vcoco_000000542982.jpg
-vcoco_000000295916.jpg
-vcoco_000000540209.jpg
-vcoco_000000236432.jpg
-vcoco_000000543831.jpg
-vcoco_000000464140.jpg
-vcoco_000000384346.jpg
-vcoco_000000468249.jpg
-vcoco_000000237677.jpg
-vcoco_000000061747.jpg
-vcoco_000000472659.jpg
-vcoco_000000400794.jpg
-vcoco_000000341429.jpg
-vcoco_000000079495.jpg
-vcoco_000000368586.jpg
-vcoco_000000305104.jpg
-vcoco_000000273889.jpg
-vcoco_000000163962.jpg
-vcoco_000000420711.jpg
-vcoco_000000448759.jpg
-vcoco_000000334410.jpg
-vcoco_000000427223.jpg
-vcoco_000000183214.jpg
-vcoco_000000232227.jpg
-vcoco_000000339336.jpg
-vcoco_000000145335.jpg
-vcoco_000000461063.jpg
-vcoco_000000121570.jpg
-vcoco_000000061414.jpg
-vcoco_000000011129.jpg
-vcoco_000000187765.jpg
-vcoco_000000114352.jpg
-vcoco_000000549284.jpg
-vcoco_000000553788.jpg
-vcoco_000000507171.jpg
-vcoco_000000431991.jpg
-vcoco_000000057283.jpg
-vcoco_000000023927.jpg
-vcoco_000000341921.jpg
-vcoco_000000233915.jpg
-vcoco_000000403489.jpg
-vcoco_000000033055.jpg
-vcoco_000000465878.jpg
-vcoco_000000283294.jpg
-vcoco_000000524924.jpg
-vcoco_000000245729.jpg
-vcoco_000000405574.jpg
-vcoco_000000515301.jpg
-vcoco_000000231645.jpg
-vcoco_000000533394.jpg
-vcoco_000000079070.jpg
-vcoco_000000251750.jpg
-vcoco_000000292187.jpg
-vcoco_000000407650.jpg
-vcoco_000000516474.jpg
-vcoco_000000488395.jpg
-vcoco_000000014801.jpg
-vcoco_000000046419.jpg
-vcoco_000000186899.jpg
-vcoco_000000419076.jpg
-vcoco_000000513456.jpg
-vcoco_000000484614.jpg
-vcoco_000000043829.jpg
-vcoco_000000420649.jpg
-vcoco_000000221562.jpg
-vcoco_000000322145.jpg
-vcoco_000000119494.jpg
-vcoco_000000036333.jpg
-vcoco_000000343608.jpg
-vcoco_000000233242.jpg
-vcoco_000000385753.jpg
-vcoco_000000456895.jpg
-vcoco_000000407139.jpg
-vcoco_000000441900.jpg
-vcoco_000000459645.jpg
-vcoco_000000346313.jpg
-vcoco_000000327174.jpg
-vcoco_000000441459.jpg
-vcoco_000000020599.jpg
-vcoco_000000462186.jpg
-vcoco_000000185697.jpg
-vcoco_000000554354.jpg
-vcoco_000000482735.jpg
-vcoco_000000463884.jpg
-vcoco_000000389554.jpg
-vcoco_000000068205.jpg
-vcoco_000000357383.jpg
-vcoco_000000158818.jpg
-vcoco_000000442961.jpg
-vcoco_000000512436.jpg
-vcoco_000000049893.jpg
-vcoco_000000492677.jpg
-vcoco_000000421361.jpg
-vcoco_000000180606.jpg
-vcoco_000000414385.jpg
-vcoco_000000406129.jpg
-vcoco_000000154567.jpg
-vcoco_000000445101.jpg
-vcoco_000000364102.jpg
-vcoco_000000014151.jpg
-vcoco_000000475229.jpg
-vcoco_000000016344.jpg
-vcoco_000000018728.jpg
-vcoco_000000393699.jpg
-vcoco_000000273155.jpg
-vcoco_000000135604.jpg
-vcoco_000000239130.jpg
-vcoco_000000296492.jpg
-vcoco_000000185598.jpg
-vcoco_000000290224.jpg
-vcoco_000000373078.jpg
-vcoco_000000263834.jpg
-vcoco_000000530998.jpg
-vcoco_000000488707.jpg
-vcoco_000000249561.jpg
-vcoco_000000433845.jpg
-vcoco_000000565993.jpg
-vcoco_000000408239.jpg
-vcoco_000000304336.jpg
-vcoco_000000437331.jpg
-vcoco_000000552254.jpg
-vcoco_000000231153.jpg
-vcoco_000000490437.jpg
-vcoco_000000495523.jpg
-vcoco_000000129563.jpg
-vcoco_000000463576.jpg
-vcoco_000000574506.jpg
-vcoco_000000172315.jpg
-vcoco_000000519479.jpg
-vcoco_000000526458.jpg
-vcoco_000000326284.jpg
-vcoco_000000403975.jpg
-vcoco_000000391284.jpg
-vcoco_000000329604.jpg
-vcoco_000000082622.jpg
-vcoco_000000348636.jpg
-vcoco_000000419333.jpg
-vcoco_000000579042.jpg
-vcoco_000000381789.jpg
-vcoco_000000248170.jpg
-vcoco_000000276055.jpg
-vcoco_000000245067.jpg
-vcoco_000000206747.jpg
-vcoco_000000378670.jpg
-vcoco_000000414578.jpg
-vcoco_000000000589.jpg
-vcoco_000000441598.jpg
-vcoco_000000282680.jpg
-vcoco_000000491681.jpg
-vcoco_000000522637.jpg
-vcoco_000000287402.jpg
-vcoco_000000444913.jpg
-vcoco_000000379980.jpg
-vcoco_000000563349.jpg
-vcoco_000000354144.jpg
-vcoco_000000246656.jpg
-vcoco_000000070733.jpg
-vcoco_000000345154.jpg
-vcoco_000000085974.jpg
-vcoco_000000482750.jpg
-vcoco_000000530558.jpg
-vcoco_000000389974.jpg
-vcoco_000000460837.jpg
-vcoco_000000417016.jpg
-vcoco_000000158107.jpg
-vcoco_000000004567.jpg
-vcoco_000000361623.jpg
-vcoco_000000315025.jpg
-vcoco_000000348631.jpg
-vcoco_000000558066.jpg
-vcoco_000000109992.jpg
-vcoco_000000367582.jpg
-vcoco_000000011625.jpg
-vcoco_000000437831.jpg
-vcoco_000000355762.jpg
-vcoco_000000581124.jpg
-vcoco_000000089052.jpg
-vcoco_000000562296.jpg
-vcoco_000000489339.jpg
-vcoco_000000102903.jpg
-vcoco_000000349897.jpg
-vcoco_000000501339.jpg
-vcoco_000000069440.jpg
-vcoco_000000434548.jpg
-vcoco_000000532055.jpg
-vcoco_000000279197.jpg
-vcoco_000000157102.jpg
-vcoco_000000067974.jpg
-vcoco_000000007977.jpg
-vcoco_000000254454.jpg
-vcoco_000000494309.jpg
-vcoco_000000380636.jpg
-vcoco_000000261732.jpg
-vcoco_000000378116.jpg
-vcoco_000000145385.jpg
-vcoco_000000525702.jpg
-vcoco_000000265815.jpg
-vcoco_000000512944.jpg
-vcoco_000000347482.jpg
-vcoco_000000073446.jpg
-vcoco_000000484701.jpg
-vcoco_000000556332.jpg
-vcoco_000000064189.jpg
-vcoco_000000396975.jpg
-vcoco_000000308759.jpg
-vcoco_000000283750.jpg
-vcoco_000000290282.jpg
-vcoco_000000546987.jpg
-vcoco_000000456485.jpg
-vcoco_000000093612.jpg
-vcoco_000000230315.jpg
-vcoco_000000490279.jpg
-vcoco_000000441518.jpg
-vcoco_000000048564.jpg
-vcoco_000000484599.jpg
-vcoco_000000400010.jpg
-vcoco_000000286425.jpg
-vcoco_000000434580.jpg
-vcoco_000000562045.jpg
-vcoco_000000258043.jpg
-vcoco_000000305319.jpg
-vcoco_000000499979.jpg
-vcoco_000000364994.jpg
-vcoco_000000324232.jpg
-vcoco_000000424303.jpg
-vcoco_000000550023.jpg
-vcoco_000000398076.jpg
-vcoco_000000053410.jpg
-vcoco_000000578861.jpg
-vcoco_000000153909.jpg
-vcoco_000000527493.jpg
-vcoco_000000330901.jpg
-vcoco_000000166376.jpg
-vcoco_000000188137.jpg
-vcoco_000000429158.jpg
-vcoco_000000075682.jpg
-vcoco_000000069320.jpg
-vcoco_000000424225.jpg
-vcoco_000000357743.jpg
-vcoco_000000562581.jpg
-vcoco_000000556966.jpg
-vcoco_000000469067.jpg
-vcoco_000000417700.jpg
-vcoco_000000558826.jpg
-vcoco_000000438504.jpg
-vcoco_000000171139.jpg
-vcoco_000000537316.jpg
-vcoco_000000296033.jpg
-vcoco_000000356490.jpg
-vcoco_000000067975.jpg
-vcoco_000000433637.jpg
-vcoco_000000073753.jpg
-vcoco_000000335594.jpg
-vcoco_000000539573.jpg
-vcoco_000000303342.jpg
-vcoco_000000412399.jpg
-vcoco_000000519631.jpg
-vcoco_000000046441.jpg
-vcoco_000000437452.jpg
-vcoco_000000278203.jpg
-vcoco_000000563849.jpg
-vcoco_000000469274.jpg
-vcoco_000000460240.jpg
-vcoco_000000361397.jpg
-vcoco_000000355297.jpg
-vcoco_000000418034.jpg
-vcoco_000000374702.jpg
-vcoco_000000376366.jpg
-vcoco_000000456433.jpg
-vcoco_000000564738.jpg
-vcoco_000000278853.jpg
-vcoco_000000436302.jpg
-vcoco_000000580466.jpg
-vcoco_000000297326.jpg
-vcoco_000000402396.jpg
-vcoco_000000574460.jpg
-vcoco_000000549361.jpg
-vcoco_000000527704.jpg
-vcoco_000000156192.jpg
-vcoco_000000365735.jpg
-vcoco_000000431494.jpg
-vcoco_000000117987.jpg
-vcoco_000000429170.jpg
-vcoco_000000535770.jpg
-vcoco_000000412788.jpg
-vcoco_000000233266.jpg
-vcoco_000000424548.jpg
-vcoco_000000444152.jpg
-vcoco_000000303429.jpg
-vcoco_000000493742.jpg
-vcoco_000000465911.jpg
-vcoco_000000463174.jpg
-vcoco_000000037039.jpg
-vcoco_000000347346.jpg
-vcoco_000000313914.jpg
-vcoco_000000561337.jpg
-vcoco_000000015140.jpg
-vcoco_000000398781.jpg
-vcoco_000000563951.jpg
-vcoco_000000350360.jpg
-vcoco_000000136687.jpg
-vcoco_000000449114.jpg
-vcoco_000000577928.jpg
-vcoco_000000049858.jpg
-vcoco_000000555271.jpg
-vcoco_000000228413.jpg
-vcoco_000000460346.jpg
-vcoco_000000382855.jpg
-vcoco_000000519744.jpg
-vcoco_000000456950.jpg
-vcoco_000000431062.jpg
-vcoco_000000419171.jpg
-vcoco_000000109229.jpg
-vcoco_000000056118.jpg
-vcoco_000000310981.jpg
-vcoco_000000027972.jpg
-vcoco_000000244646.jpg
-vcoco_000000294634.jpg
-vcoco_000000134496.jpg
-vcoco_000000213790.jpg
-vcoco_000000313313.jpg
-vcoco_000000070296.jpg
-vcoco_000000561809.jpg
-vcoco_000000563927.jpg
-vcoco_000000396853.jpg
-vcoco_000000147331.jpg
-vcoco_000000512211.jpg
-vcoco_000000538122.jpg
-vcoco_000000037655.jpg
-vcoco_000000414670.jpg
-vcoco_000000361046.jpg
-vcoco_000000143263.jpg
-vcoco_000000415153.jpg
-vcoco_000000475191.jpg
-vcoco_000000491130.jpg
-vcoco_000000172597.jpg
-vcoco_000000192095.jpg
-vcoco_000000571012.jpg
-vcoco_000000236068.jpg
-vcoco_000000564515.jpg
-vcoco_000000117508.jpg
-vcoco_000000435910.jpg
-vcoco_000000455334.jpg
-vcoco_000000308576.jpg
-vcoco_000000134589.jpg
-vcoco_000000055857.jpg
-vcoco_000000057062.jpg
-vcoco_000000202339.jpg
-vcoco_000000402118.jpg
-vcoco_000000580381.jpg
-vcoco_000000533315.jpg
-vcoco_000000146963.jpg
-vcoco_000000534906.jpg
-vcoco_000000110618.jpg
-vcoco_000000465556.jpg
-vcoco_000000347390.jpg
-vcoco_000000416473.jpg
-vcoco_000000358206.jpg
-vcoco_000000028547.jpg
-vcoco_000000302958.jpg
-vcoco_000000464789.jpg
-vcoco_000000438807.jpg
-vcoco_000000565612.jpg
-vcoco_000000010579.jpg
-vcoco_000000472757.jpg
-vcoco_000000433547.jpg
-vcoco_000000294863.jpg
-vcoco_000000063721.jpg
-vcoco_000000204049.jpg
-vcoco_000000574961.jpg
-vcoco_000000491090.jpg
-vcoco_000000552065.jpg
-vcoco_000000416267.jpg
-vcoco_000000525546.jpg
-vcoco_000000136672.jpg
-vcoco_000000018704.jpg
-vcoco_000000552985.jpg
-vcoco_000000412285.jpg
-vcoco_000000400907.jpg
-vcoco_000000501515.jpg
-vcoco_000000512827.jpg
-vcoco_000000293275.jpg
-vcoco_000000551849.jpg
-vcoco_000000171210.jpg
-vcoco_000000383046.jpg
-vcoco_000000284648.jpg
-vcoco_000000177069.jpg
-vcoco_000000274970.jpg
-vcoco_000000299859.jpg
-vcoco_000000447911.jpg
-vcoco_000000162530.jpg
-vcoco_000000430581.jpg
-vcoco_000000562192.jpg
-vcoco_000000345559.jpg
-vcoco_000000541374.jpg
-vcoco_000000151084.jpg
-vcoco_000000391046.jpg
-vcoco_000000002583.jpg
-vcoco_000000094593.jpg
-vcoco_000000263403.jpg
-vcoco_000000167962.jpg
-vcoco_000000577277.jpg
-vcoco_000000198198.jpg
-vcoco_000000461110.jpg
-vcoco_000000393569.jpg
-vcoco_000000497668.jpg
-vcoco_000000434193.jpg
-vcoco_000000550365.jpg
-vcoco_000000184978.jpg
-vcoco_000000549055.jpg
-vcoco_000000531739.jpg
-vcoco_000000215280.jpg
-vcoco_000000482810.jpg
-vcoco_000000261977.jpg
-vcoco_000000305195.jpg
-vcoco_000000425798.jpg
-vcoco_000000327864.jpg
-vcoco_000000380100.jpg
-vcoco_000000539529.jpg
-vcoco_000000507935.jpg
-vcoco_000000578849.jpg
-vcoco_000000414373.jpg
-vcoco_000000239930.jpg
-vcoco_000000204726.jpg
-vcoco_000000251576.jpg
-vcoco_000000507211.jpg
-vcoco_000000474601.jpg
-vcoco_000000355257.jpg
-vcoco_000000537905.jpg
-vcoco_000000580507.jpg
-vcoco_000000336015.jpg
-vcoco_000000290398.jpg
-vcoco_000000137682.jpg
-vcoco_000000534210.jpg
-vcoco_000000141887.jpg
-vcoco_000000396941.jpg
-vcoco_000000192039.jpg
-vcoco_000000442348.jpg
-vcoco_000000246001.jpg
-vcoco_000000082715.jpg
-vcoco_000000192932.jpg
-vcoco_000000328144.jpg
-vcoco_000000364126.jpg
-vcoco_000000034993.jpg
-vcoco_000000170852.jpg
-vcoco_000000373785.jpg
-vcoco_000000505265.jpg
-vcoco_000000327417.jpg
-vcoco_000000489944.jpg
-vcoco_000000298362.jpg
-vcoco_000000524638.jpg
-vcoco_000000364283.jpg
-vcoco_000000075587.jpg
-vcoco_000000459641.jpg
-vcoco_000000138861.jpg
-vcoco_000000063563.jpg
-vcoco_000000108879.jpg
-vcoco_000000388381.jpg
-vcoco_000000113041.jpg
-vcoco_000000551215.jpg
-vcoco_000000072281.jpg
-vcoco_000000286171.jpg
-vcoco_000000200058.jpg
-vcoco_000000380609.jpg
-vcoco_000000328397.jpg
-vcoco_000000564289.jpg
-vcoco_000000518273.jpg
-vcoco_000000399129.jpg
-vcoco_000000202115.jpg
-vcoco_000000399983.jpg
-vcoco_000000377159.jpg
-vcoco_000000525170.jpg
-vcoco_000000492881.jpg
-vcoco_000000071313.jpg
-vcoco_000000049891.jpg
-vcoco_000000264572.jpg
-vcoco_000000415872.jpg
-vcoco_000000163682.jpg
-vcoco_000000430036.jpg
-vcoco_000000287038.jpg
-vcoco_000000334301.jpg
-vcoco_000000137387.jpg
-vcoco_000000137315.jpg
-vcoco_000000166297.jpg
-vcoco_000000275448.jpg
-vcoco_000000558457.jpg
-vcoco_000000355918.jpg
-vcoco_000000495525.jpg
-vcoco_000000394286.jpg
-vcoco_000000013867.jpg
-vcoco_000000526082.jpg
-vcoco_000000511929.jpg
-vcoco_000000412062.jpg
-vcoco_000000494113.jpg
-vcoco_000000473133.jpg
-vcoco_000000529283.jpg
-vcoco_000000452060.jpg
-vcoco_000000528471.jpg
-vcoco_000000460857.jpg
-vcoco_000000561383.jpg
-vcoco_000000140633.jpg
-vcoco_000000461647.jpg
-vcoco_000000350668.jpg
-vcoco_000000560646.jpg
-vcoco_000000206912.jpg
-vcoco_000000381826.jpg
-vcoco_000000109679.jpg
-vcoco_000000546670.jpg
-vcoco_000000514950.jpg
-vcoco_000000046042.jpg
-vcoco_000000006380.jpg
-vcoco_000000559145.jpg
-vcoco_000000490400.jpg
-vcoco_000000350160.jpg
-vcoco_000000001108.jpg
-vcoco_000000436183.jpg
-vcoco_000000321258.jpg
-vcoco_000000572505.jpg
-vcoco_000000048489.jpg
-vcoco_000000330920.jpg
-vcoco_000000270275.jpg
-vcoco_000000547428.jpg
-vcoco_000000147488.jpg
-vcoco_000000558839.jpg
-vcoco_000000078061.jpg
-vcoco_000000485943.jpg
-vcoco_000000525762.jpg
-vcoco_000000117584.jpg
-vcoco_000000096304.jpg
-vcoco_000000147088.jpg
-vcoco_000000434510.jpg
-vcoco_000000301604.jpg
-vcoco_000000319350.jpg
-vcoco_000000292988.jpg
-vcoco_000000467612.jpg
-vcoco_000000561042.jpg
-vcoco_000000401167.jpg
-vcoco_000000563885.jpg
-vcoco_000000548318.jpg
-vcoco_000000304008.jpg
-vcoco_000000128570.jpg
-vcoco_000000529139.jpg
-vcoco_000000195568.jpg
-vcoco_000000339986.jpg
-vcoco_000000221864.jpg
-vcoco_000000536977.jpg
-vcoco_000000315603.jpg
-vcoco_000000135288.jpg
-vcoco_000000560108.jpg
-vcoco_000000556018.jpg
-vcoco_000000553609.jpg
-vcoco_000000459991.jpg
-vcoco_000000401244.jpg
-vcoco_000000304757.jpg
-vcoco_000000430369.jpg
-vcoco_000000119640.jpg
-vcoco_000000153380.jpg
-vcoco_000000480116.jpg
-vcoco_000000012991.jpg
-vcoco_000000461860.jpg
-vcoco_000000331298.jpg
-vcoco_000000349750.jpg
-vcoco_000000278204.jpg
-vcoco_000000129784.jpg
-vcoco_000000532493.jpg
-vcoco_000000313848.jpg
-vcoco_000000513077.jpg
-vcoco_000000188375.jpg
-vcoco_000000345855.jpg
-vcoco_000000295740.jpg
-vcoco_000000398423.jpg
-vcoco_000000106664.jpg
-vcoco_000000386116.jpg
-vcoco_000000500019.jpg
-vcoco_000000254368.jpg
-vcoco_000000286460.jpg
-vcoco_000000278323.jpg
-vcoco_000000459078.jpg
-vcoco_000000204075.jpg
-vcoco_000000094350.jpg
-vcoco_000000365187.jpg
-vcoco_000000312439.jpg
-vcoco_000000348263.jpg
-vcoco_000000332352.jpg
-vcoco_000000123013.jpg
-vcoco_000000499105.jpg
-vcoco_000000320396.jpg
-vcoco_000000052016.jpg
-vcoco_000000096705.jpg
-vcoco_000000143101.jpg
-vcoco_000000404766.jpg
-vcoco_000000404367.jpg
-vcoco_000000511670.jpg
-vcoco_000000363826.jpg
-vcoco_000000487957.jpg
-vcoco_000000430610.jpg
-vcoco_000000029931.jpg
-vcoco_000000189831.jpg
-vcoco_000000301247.jpg
-vcoco_000000489739.jpg
-vcoco_000000576468.jpg
-vcoco_000000324036.jpg
-vcoco_000000304834.jpg
-vcoco_000000581328.jpg
-vcoco_000000083408.jpg
-vcoco_000000440840.jpg
-vcoco_000000557685.jpg
-vcoco_000000235994.jpg
-vcoco_000000118614.jpg
-vcoco_000000465422.jpg
-vcoco_000000300408.jpg
-vcoco_000000094607.jpg
-vcoco_000000052803.jpg
-vcoco_000000281534.jpg
-vcoco_000000401897.jpg
-vcoco_000000292647.jpg
-vcoco_000000425361.jpg
-vcoco_000000312269.jpg
-vcoco_000000556883.jpg
-vcoco_000000038721.jpg
-vcoco_000000053464.jpg
-vcoco_000000016737.jpg
-vcoco_000000556108.jpg
-vcoco_000000044057.jpg
-vcoco_000000308996.jpg
-vcoco_000000187574.jpg
-vcoco_000000563945.jpg
-vcoco_000000097278.jpg
-vcoco_000000011591.jpg
-vcoco_000000497082.jpg
-vcoco_000000513292.jpg
-vcoco_000000480663.jpg
-vcoco_000000037325.jpg
-vcoco_000000342523.jpg
-vcoco_000000334671.jpg
-vcoco_000000535251.jpg
-vcoco_000000080273.jpg
-vcoco_000000422560.jpg
-vcoco_000000543644.jpg
-vcoco_000000406982.jpg
-vcoco_000000301541.jpg
-vcoco_000000434930.jpg
-vcoco_000000431893.jpg
-vcoco_000000535179.jpg
-vcoco_000000316237.jpg
-vcoco_000000577875.jpg
-vcoco_000000439443.jpg
-vcoco_000000033731.jpg
-vcoco_000000573065.jpg
-vcoco_000000029719.jpg
-vcoco_000000475765.jpg
-vcoco_000000357898.jpg
-vcoco_000000351793.jpg
-vcoco_000000574805.jpg
-vcoco_000000027221.jpg
-vcoco_000000493628.jpg
-vcoco_000000199553.jpg
-vcoco_000000056433.jpg
-vcoco_000000134193.jpg
-vcoco_000000298344.jpg
-vcoco_000000124979.jpg
-vcoco_000000378831.jpg
-vcoco_000000467887.jpg
-vcoco_000000558134.jpg
-vcoco_000000300786.jpg
-vcoco_000000505309.jpg
-vcoco_000000484575.jpg
-vcoco_000000416973.jpg
-vcoco_000000457021.jpg
-vcoco_000000159731.jpg
-vcoco_000000442225.jpg
-vcoco_000000168335.jpg
-vcoco_000000210249.jpg
-vcoco_000000343704.jpg
-vcoco_000000385861.jpg
-vcoco_000000388512.jpg
-vcoco_000000154861.jpg
-vcoco_000000257421.jpg
-vcoco_000000277418.jpg
-vcoco_000000566908.jpg
-vcoco_000000039643.jpg
-vcoco_000000378454.jpg
-vcoco_000000214127.jpg
-vcoco_000000270871.jpg
-vcoco_000000484849.jpg
-vcoco_000000346352.jpg
-vcoco_000000299869.jpg
-vcoco_000000037102.jpg
-vcoco_000000146676.jpg
-vcoco_000000154254.jpg
-vcoco_000000467477.jpg
-vcoco_000000448113.jpg
-vcoco_000000399885.jpg
-vcoco_000000575921.jpg
-vcoco_000000307426.jpg
-vcoco_000000478338.jpg
-vcoco_000000433136.jpg
-vcoco_000000359589.jpg
-vcoco_000000520150.jpg
-vcoco_000000339611.jpg
-vcoco_000000285505.jpg
-vcoco_000000472024.jpg
-vcoco_000000144582.jpg
-vcoco_000000540834.jpg
-vcoco_000000397809.jpg
-vcoco_000000102935.jpg
-vcoco_000000052433.jpg
-vcoco_000000038828.jpg
-vcoco_000000379180.jpg
-vcoco_000000152202.jpg
-vcoco_000000199555.jpg
-vcoco_000000314356.jpg
-vcoco_000000208995.jpg
-vcoco_000000314694.jpg
-vcoco_000000171384.jpg
-vcoco_000000580235.jpg
-vcoco_000000563031.jpg
-vcoco_000000499705.jpg
-vcoco_000000367622.jpg
-vcoco_000000559388.jpg
-vcoco_000000412001.jpg
-vcoco_000000247134.jpg
-vcoco_000000058869.jpg
-vcoco_000000078925.jpg
-vcoco_000000527480.jpg
-vcoco_000000221378.jpg
-vcoco_000000158428.jpg
-vcoco_000000327436.jpg
-vcoco_000000283524.jpg
-vcoco_000000209468.jpg
-vcoco_000000454143.jpg
-vcoco_000000311116.jpg
-vcoco_000000357971.jpg
-vcoco_000000401428.jpg
-vcoco_000000360434.jpg
-vcoco_000000290415.jpg
-vcoco_000000474024.jpg
-vcoco_000000416625.jpg
-vcoco_000000010534.jpg
-vcoco_000000369529.jpg
-vcoco_000000178184.jpg
-vcoco_000000502440.jpg
-vcoco_000000551608.jpg
-vcoco_000000534395.jpg
-vcoco_000000458932.jpg
-vcoco_000000444502.jpg
-vcoco_000000347571.jpg
-vcoco_000000464752.jpg
-vcoco_000000345288.jpg
-vcoco_000000337533.jpg
-vcoco_000000568790.jpg
-vcoco_000000391474.jpg
-vcoco_000000376793.jpg
-vcoco_000000063109.jpg
-vcoco_000000042089.jpg
-vcoco_000000347023.jpg
-vcoco_000000311015.jpg
-vcoco_000000523546.jpg
-vcoco_000000270744.jpg
-vcoco_000000109324.jpg
-vcoco_000000410554.jpg
-vcoco_000000456552.jpg
-vcoco_000000574343.jpg
-vcoco_000000263647.jpg
-vcoco_000000178285.jpg
-vcoco_000000561062.jpg
-vcoco_000000299768.jpg
-vcoco_000000497514.jpg
-vcoco_000000171622.jpg
-vcoco_000000485742.jpg
-vcoco_000000112029.jpg
-vcoco_000000114661.jpg
-vcoco_000000371414.jpg
-vcoco_000000191350.jpg
-vcoco_000000448958.jpg
-vcoco_000000516846.jpg
-vcoco_000000113052.jpg
-vcoco_000000336479.jpg
-vcoco_000000252468.jpg
-vcoco_000000474854.jpg
-vcoco_000000187336.jpg
-vcoco_000000075494.jpg
-vcoco_000000422274.jpg
-vcoco_000000082106.jpg
-vcoco_000000227186.jpg
-vcoco_000000438126.jpg
-vcoco_000000114917.jpg
-vcoco_000000419644.jpg
-vcoco_000000400829.jpg
-vcoco_000000209035.jpg
-vcoco_000000557408.jpg
-vcoco_000000441228.jpg
-vcoco_000000340069.jpg
-vcoco_000000131580.jpg
-vcoco_000000414522.jpg
-vcoco_000000361860.jpg
-vcoco_000000495578.jpg
-vcoco_000000468985.jpg
-vcoco_000000419159.jpg
-vcoco_000000368222.jpg
-vcoco_000000138704.jpg
-vcoco_000000079305.jpg
-vcoco_000000256875.jpg
-vcoco_000000378244.jpg
-vcoco_000000058801.jpg
-vcoco_000000447663.jpg
-vcoco_000000422689.jpg
-vcoco_000000577073.jpg
-vcoco_000000113334.jpg
-vcoco_000000107584.jpg
-vcoco_000000392055.jpg
-vcoco_000000531385.jpg
-vcoco_000000405529.jpg
-vcoco_000000168746.jpg
-vcoco_000000463242.jpg
-vcoco_000000411472.jpg
-vcoco_000000431085.jpg
-vcoco_000000365095.jpg
-vcoco_000000191093.jpg
-vcoco_000000479829.jpg
-vcoco_000000361594.jpg
-vcoco_000000286174.jpg
-vcoco_000000035705.jpg
-vcoco_000000439801.jpg
-vcoco_000000264279.jpg
-vcoco_000000061693.jpg
-vcoco_000000386474.jpg
-vcoco_000000077577.jpg
-vcoco_000000532775.jpg
-vcoco_000000288712.jpg
-vcoco_000000183872.jpg
-vcoco_000000377816.jpg
-vcoco_000000365557.jpg
-vcoco_000000048747.jpg
-vcoco_000000531960.jpg
-vcoco_000000426421.jpg
-vcoco_000000462208.jpg
-vcoco_000000444263.jpg
-vcoco_000000103267.jpg
-vcoco_000000173514.jpg
-vcoco_000000420231.jpg
-vcoco_000000410056.jpg
-vcoco_000000428718.jpg
-vcoco_000000430789.jpg
-vcoco_000000005689.jpg
-vcoco_000000410052.jpg
-vcoco_000000578427.jpg
-vcoco_000000323379.jpg
-vcoco_000000480629.jpg
-vcoco_000000408120.jpg
-vcoco_000000508328.jpg
-vcoco_000000442084.jpg
-vcoco_000000560718.jpg
-vcoco_000000519795.jpg
-vcoco_000000357690.jpg
-vcoco_000000564341.jpg
-vcoco_000000192835.jpg
-vcoco_000000044171.jpg
-vcoco_000000291009.jpg
-vcoco_000000284379.jpg
-vcoco_000000576589.jpg
-vcoco_000000570760.jpg
-vcoco_000000082551.jpg
-vcoco_000000479939.jpg
-vcoco_000000046990.jpg
-vcoco_000000476864.jpg
-vcoco_000000134053.jpg
-vcoco_000000232972.jpg
-vcoco_000000288421.jpg
-vcoco_000000013815.jpg
-vcoco_000000326666.jpg
-vcoco_000000321006.jpg
-vcoco_000000406533.jpg
-vcoco_000000486178.jpg
-vcoco_000000368949.jpg
-vcoco_000000463678.jpg
-vcoco_000000126301.jpg

hot_analysis/hico_analysis.ipynb

@@ -1,342 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import json\n",
-    "import pandas as pd \n",
-    "import ipdb\n",
-    "import os\n",
-    "import pickle as pkl\n",
-    "import os.path as osp\n",
-    "import numpy as np\n",
-    "from PIL import Image\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Total images found: 9642\n",
-      "Images after KP filtering: 3895\n",
-      "['hake_train2015_HICO_train2015_00005476.jpg', 'hake_train2015_HICO_train2015_00008329.jpg', 'hake_train2015_HICO_train2015_00008027.jpg', 'hake_train2015_HICO_train2015_00013408.jpg', 'hake_train2015_HICO_train2015_00010656.jpg']\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Load Agniv VITpose-base hico filtering\n",
-    "filter_path = './agniv_pose_filter/hico.npy'\n",
-    "pose_md = np.load(filter_path, allow_pickle=True)\n",
-    "pose_md = pose_md.item()\n",
-    "filter_img_names = {}\n",
-    "\n",
-    "print(f'Total images found: {len(pose_md)}')\n",
-    "\n",
-    "# Filter out images with < 10 visible keypoints \n",
-    "kp_thresh = 10\n",
-    "\n",
-    "for imgname, pose_num in pose_md.items():\n",
-    "    if pose_num > kp_thresh:\n",
-    "        filter_img_names[imgname] = pose_num\n",
-    "        \n",
-    "print(f'Images after KP filtering: {len(filter_img_names)}')\n",
-    "\n",
-    "print(list(filter_img_names.keys())[:5])\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Load Agniv VITpose-base hot dict\n",
-    "# filter_path = \"./agniv_pose_filter/hot_dict.pkl\"\n",
-    "# with open(filter_path, 'rb') as f:\n",
-    "#     pose_md_dict = pkl.load(f)\n",
-    "    \n",
-    "# hico_dict = {}\n",
-    "\n",
-    "# for k, v in pose_md_dict.items():\n",
-    "#     if 'hake' in k:\n",
-    "#         hico_dict[k] = v\n",
-    "    \n",
-    "# print(f'Total images found: {len(hico_dict)}')\n",
-    "\n",
-    "# # Filter out images with < 10 visible keypoints \n",
-    "# kp_thresh = 10\n",
-    "\n",
-    "# filter_img_names = {}\n",
-    "\n",
-    "# for imgname, kp_md in hico_dict.items():\n",
-    "#     if kp_md == 0:\n",
-    "#         continue\n",
-    "#     if kp_md[\"num_persons\"] == 1 and kp_md[\"num_kpt\"][0.5][0] > kp_thresh:\n",
-    "#         filter_img_names[imgname] = kp_md[\"num_kpt\"][0.5][0]\n",
-    "        \n",
-    "# print(f'Images after KP filtering: {len(filter_img_names)}')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "       0         1               2\n",
-      "0      1  airplane           board\n",
-      "1      2  airplane          direct\n",
-      "2      3  airplane            exit\n",
-      "3      4  airplane             fly\n",
-      "4      5  airplane         inspect\n",
-      "..   ...       ...             ...\n",
-      "595  596     zebra            feed\n",
-      "596  597     zebra            hold\n",
-      "597  598     zebra             pet\n",
-      "598  599     zebra           watch\n",
-      "599  600     zebra  no_interaction\n",
-      "\n",
-      "[600 rows x 3 columns]\n"
-     ]
-    }
-   ],
-   "source": [
-    "\n",
-    "hico_annot = json.load(open('/ps/project/datasets/HICO/hico-image-level/hico-training-set-image-level.json', 'rb'))\n",
-    "hoi_mapping = pd.read_csv('/ps/project/datasets/HICO/hico-image-level/hico_hoi_list.txt', header=None, delim_whitespace=True)\n",
-    "print(hoi_mapping)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Final number of images 3154\n"
-     ]
-    }
-   ],
-   "source": [
-    "version = '1'\n",
-    "out_dir = f'./filtered_data/v_{version}'\n",
-    "os.makedirs(out_dir, exist_ok=True)\n",
-    "\n",
-    "objectwise_img_names = {}\n",
-    "imgwise_object_names = {}\n",
-    "img_dir = '/ps/project/datasets/HICO/hico_20150920/images/train2015'\n",
-    "\n",
-    "bad_object_names = ['bear', 'bird', 'cat', 'cow', \n",
-    "                    'dog', 'elephant', 'giraffe', 'horse', \n",
-    "                   'mouse', 'person', 'sheep', 'zebra' ]\n",
-    "bad_action_names = ['buy', 'chase', 'direct', 'greet', 'herd', 'hose',\n",
-    "                   'hug', 'hunt', 'milk', 'no_interaction', 'pet', 'point', 'teach',\n",
-    "                   'watch', 'wave']\n",
-    "\n",
-    "for i, (img_name, img_md) in enumerate(hico_annot.items()):\n",
-    "    \n",
-    "    # Apply keypoint number filtering on the images \n",
-    "    full_img_name = 'hake_train2015_' + img_name\n",
-    "    if full_img_name not in filter_img_names.keys():\n",
-    "        continue\n",
-    "    \n",
-    "    # show the image\n",
-    "    if i < 0:\n",
-    "        img = Image.open(osp.join(img_dir,img_name))\n",
-    "        display(img)\n",
-    "    \n",
-    "    obj_names = []\n",
-    "    action_names = []\n",
-    "    kp_num = filter_img_names[full_img_name]\n",
-    "    \n",
-    "    # travel through all hoi in the metadata, save obj_names and action_names for the hois\n",
-    "    for hoi_id in img_md['hoi_id']:\n",
-    "        img_md_row = hoi_mapping.loc[hoi_mapping[0] == hoi_id].iloc[0]\n",
-    "\n",
-    "        obj_name = img_md_row[1]\n",
-    "        if obj_name in bad_object_names:\n",
-    "            continue\n",
-    "        action_name = img_md_row[2]\n",
-    "        if action_name in bad_action_names:\n",
-    "            continue\n",
-    "            \n",
-    "        obj_names.append(obj_name)\n",
-    "        action_names.append(action_name)\n",
-    "        \n",
-    "    if len(set(obj_names)) == 0 or len(action_names) == 0:\n",
-    "        continue\n",
-    "    \n",
-    "    imgwise_object_names.setdefault(full_img_name,[]).extend(list(set(obj_names)))\n",
-    "    \n",
-    "# #     # Display images with multiple objects\n",
-    "#     if len(set(obj_names)) > 1:\n",
-    "#         print(img_name)\n",
-    "#         print(obj_names)\n",
-    "#         print(action_names)\n",
-    "#         print(f'Number of Kps: {kp_num}')\n",
-    "#         img = Image.open(osp.join(img_dir,img_name))\n",
-    "#         display(img)\n",
-    "            \n",
-    "    for obj_name in set(obj_names):\n",
-    "        objectwise_img_names.setdefault(obj_name,[]).append(full_img_name)\n",
-    "        \n",
-    "print(f'Final number of images {len(imgwise_object_names)}')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "saved at ./filtered_data/v_1/object_per_image_dict.json\n",
-      "saved at ./filtered_data/v_1/imgnames_per_object_dict.json\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Save the imagewise_object dict\n",
-    "out_path = osp.join(out_dir, 'object_per_image_dict.json')\n",
-    "with open(out_path, 'w') as fp:\n",
-    "    json.dump(imgwise_object_names, fp)\n",
-    "    print(f'saved at {out_path}')\n",
-    "    \n",
-    "# # save image_list \n",
-    "# out_path = osp.join(out_dir, 'hico_imglist_all_140223.txt')\n",
-    "# with open(out_path, 'w') as f:\n",
-    "#     f.write('\\n'.join(imgwise_object_names.keys()))\n",
-    "#     print(f'saved at {out_path}')\n",
-    "\n",
-    "\n",
-    "# Save the object_wise dict\n",
-    "out_path = osp.join(out_dir, 'imgnames_per_object_dict.json')\n",
-    "with open(out_path, 'w') as fp:\n",
-    "    json.dump(objectwise_img_names, fp)\n",
-    "    print(f'saved at {out_path}')\n",
-    "\n",
-    "    \n",
-    "\n",
-    "    "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/stripathi/anaconda3/envs/cliff/lib/python3.10/site-packages/scipy/__init__.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.23.5\n",
-      "  warnings.warn(f\"A NumPy version >={np_minversion} and <{np_maxversion}\"\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "3189\n"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns\n",
-    "\n",
-    "# sort the dictionary \n",
-    "objectwise_img_names = dict(sorted(objectwise_img_names.items(), key=lambda x: len(x[1]), reverse=True))\n",
-    "\n",
-    "# Extract object names and image counts\n",
-    "obj_names = list(objectwise_img_names.keys())\n",
-    "img_counts = [len(objectwise_img_names[obj]) for obj in objectwise_img_names]\n",
-    "print(sum(img_counts))\n",
-    "\n",
-    "# Create bar plot\n",
-    "sns.barplot(x=obj_names, y=img_counts)\n",
-    "\n",
-    "# Add x-axis and y-axis labels\n",
-    "plt.xlabel('Object')\n",
-    "plt.ylabel('Number of Images')\n",
-    "\n",
-    "plt.xticks(rotation=45, ha='right', fontsize=3)\n",
-    "\n",
-    "# Save the plot as a high-resolution image file\n",
-    "out_path = osp.join(out_dir, 'image_per_object_category.png')\n",
-    "plt.savefig(out_path, dpi=300)\n",
-    "\n",
-    "# Show plot\n",
-    "plt.show()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "    "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

hot_analysis/jc_graphs/documents-export-2023-03-07/image_per_object_category.csv

@@ -1,70 +0,0 @@
-,count
-surfboard,452
-chair,287
-snowboard,280
-laptop,237
-cell phone,224
-sports ball,208
-dining table,184
-skateboard,172
-tennis racket,172
-book,171
-frisbee,160
-cup,155
-car,138
-bed,129
-bottle,123
-bench,119
-couch,113
-handbag,113
-backpack,106
-knife,89
-bowl,86
-skis,85
-baseball glove,75
-potted plant,69
-tv,67
-mouse,59
-pizza,57
-suitcase,54
-fork,52
-keyboard,50
-tie,47
-spoon,46
-remote,44
-cake,43
-truck,40
-clock,39
-sandwich,35
-bicycle,34
-umbrella,33
-wine glass,31
-boat,28
-donut,28
-oven,27
-teddy bear,26
-sink,25
-refrigerator,23
-scissors,22
-vase,21
-baseball bat,18
-kite,16
-banana,16
-hot dog,16
-traffic light,16
-motorcycle,14
-microwave,14
-apple,12
-fire hydrant,10
-carrot,9
-bus,8
-broccoli,8
-orange,8
-toilet,7
-stop sign,6
-hair drier,6
-train,4
-airplane,4
-parking meter,4
-toothbrush,3
-toaster,1

hot_analysis/jc_graphs/documents-export-2023-03-07/object_nest_piechart_data.csv

@@ -1,77 +0,0 @@
-,character,parent,value
-0,transportation,objects,0
-1,accessories,objects,0
-2,furniture,objects,0
-3,everyday objects,objects,0
-4,sports equipment,objects,0
-5,food items,objects,0
-6,kitchen appliances,objects,0
-7,motorcycle,transportation,14
-8,bicycle,transportation,129
-9,boat,transportation,33
-10,car,transportation,106
-11,truck,transportation,31
-12,bus,transportation,34
-13,train,transportation,172
-14,airplane,transportation,85
-15,backpack,accessories,280
-16,tie,accessories,171
-17,handbag,accessories,16
-18,baseball glove,accessories,43
-19,bench,furniture,113
-20,chair,furniture,452
-21,couch,furniture,75
-22,bed,furniture,123
-23,toilet,furniture,287
-24,dining table,furniture,160
-25,book,everyday objects,6
-26,umbrella,everyday objects,28
-27,cell phone,everyday objects,54
-28,laptop,everyday objects,44
-29,kite,everyday objects,16
-30,suitcase,everyday objects,119
-31,bottle,everyday objects,89
-32,remote,everyday objects,46
-33,toothbrush,everyday objects,67
-34,teddy bear,everyday objects,237
-35,scissors,everyday objects,224
-36,keyboard,everyday objects,172
-37,hair drier,everyday objects,138
-38,traffic light,everyday objects,27
-39,fire hydrant,everyday objects,208
-40,stop sign,everyday objects,12
-41,tv,everyday objects,18
-42,vase,everyday objects,26
-43,parking meter,everyday objects,113
-44,clock,everyday objects,9
-45,potted plant,everyday objects,155
-46,mouse,everyday objects,8
-47,frisbee,sports equipment,22
-48,sports ball,sports equipment,28
-49,tennis racket,sports equipment,50
-50,baseball bat,sports equipment,47
-51,skateboard,sports equipment,4
-52,snowboard,sports equipment,16
-53,skis,sports equipment,57
-54,surfboard,sports equipment,184
-55,banana,food items,6
-56,cake,food items,3
-57,apple,food items,4
-58,carrot,food items,16
-59,pizza,food items,40
-60,donut,food items,21
-61,hot dog,food items,35
-62,sandwich,food items,8
-63,broccoli,food items,7
-64,orange,food items,25
-65,knife,kitchen appliances,4
-66,spoon,kitchen appliances,52
-67,cup,kitchen appliances,86
-68,wine glass,kitchen appliances,23
-69,oven,kitchen appliances,10
-70,fork,kitchen appliances,39
-71,bowl,kitchen appliances,69
-72,refrigerator,kitchen appliances,8
-73,toaster,kitchen appliances,59
-74,sink,kitchen appliances,14
-75,microwave,kitchen appliances,1

hot_analysis/jc_graphs/documents-export-2023-03-07/partwise_contact_graph.csv

@@ -1,18 +0,0 @@
-,count
-leftFoot,8109
-rightFoot,7928
-rightHand,5085
-leftHand,3949
-spine,3694
-hips,2346
-leftUpLeg,1870
-rightUpLeg,1847
-rightForeArm,736
-rightLeg,700
-head,692
-rightShoulder,670
-leftShoulder,667
-leftForeArm,635
-leftLeg,591
-rightArm,571
-leftArm,535

hot_analysis/jc_graphs/plot_image_per_object.py

@@ -1,147 +0,0 @@
-import csv
-from pathlib import Path
-
-import matplotlib.pyplot as plt
-from matplotlib import gridspec
-import numpy as np
-import seaborn as sns
-
-# Input/output files
-CSV_FOLDER = Path(__file__).parent / "documents-export-2023-03-07"
-IMAGE_PER_OBJECT_FILE = CSV_FOLDER / "image_per_object_category.csv"
-PIE_CHART_DATA_FILE = CSV_FOLDER / "object_nest_piechart_data.csv"
-OUTPUT = 'output.pdf'
-
-# Some configuration
-FONTSIZE = 20
-FONTSIZE_PIE = 25
-COLOR_RANGE = (0.15, 0.85)  # to avoid having exterme values
-CUTOFF = 30  # min number of counts for an object to be considered
-PIE_INNER_RADIUS = 0.3  # value used for the nested pie chart
-plt.rcParams['grid.color'] = (0.5, 0.5, 0.5, 0.1)  # low grid opacity
-
-# Categories and associated objects
-categorization_unordered = {
-    "transportation": [
-        'motorcycle', 'bicycle', 'boat', 'car', 'truck', 'bus', 'train', 'airplane',],
-    "accessories": [
-        'backpack', 'tie', 'handbag', 'baseball glove'],
-    "furniture": [
-        'bench', 'chair', 'couch', 'bed', 'toilet', 'dining table'],
-    'everyday objects': [
-        'book', 'umbrella', 'cell phone', 'laptop', 'kite', 'suitcase', 'bottle', 'remote',
-        'toothbrush', 'teddy bear', 'scissors', 'keyboard', 'hair drier', 'traffic light',
-        'fire hydrant', 'stop sign', 'tv', 'vase', 'parking meter', 'clock', 'potted plant',
-        'mouse'],
-    'sports equipment': [
-        'frisbee', 'sports ball', 'tennis racket', 'baseball bat',
-        'skateboard', 'snowboard', 'skis', 'surfboard'],
-    'food items': [
-        'banana', 'cake', 'apple', 'carrot', 'pizza', 'donut', 'hot dog',
-        'sandwich', 'broccoli', 'orange'],
-    'kitchen appliances': [
-        'knife', 'spoon', 'cup', 'wine glass', 'oven', 'fork', 'bowl',
-        'refrigerator', 'toaster', 'sink', 'microwave']}
-
-# Colors for each category
-cat_colors = {
-    "transportation": plt.cm.spring,
-    "accessories": plt.cm.Greys,
-    "furniture": plt.cm.Purples,
-    "everyday objects": plt.cm.Reds,
-    "sports equipment": plt.cm.Blues,
-    "food items": plt.cm.Wistia,
-    "kitchen appliances":  plt.cm.summer}
-
-# Read CSV files
-objects = {}
-with open(IMAGE_PER_OBJECT_FILE, newline='', encoding="utf-8") as csvfile:
-    reader = csv.DictReader(csvfile)
-    for row in reader:
-        objects[row['']] = {}
-        objects[row['']]['count'] = int(row['count'])
-
-# In each caterory, order object by count in descending order
-categorization = {
-    cat: sorted(val, key=lambda _: objects[_]["count"])
-    for cat, val in categorization_unordered.items()}
-
-# Some sanity checks :)
-assert list(categorization.keys()) == list(categorization_unordered.keys())
-assert list(categorization.keys()) == list(cat_colors.keys())
-for cat in categorization:
-    assert len(categorization[cat]) == len(categorization_unordered[cat])
-    assert set(categorization[cat]) == set(categorization_unordered[cat])
-
-# Cutoff objects and categorization
-selected_objects = [o for o, v in objects.items() if v["count"] > CUTOFF]
-selected_categorization = {}
-for k, v in categorization.items():
-    selected_categorization[k] = [o for o in v if o in selected_objects]
-
-# Add a color for each object
-# All objects in one category use the same category color
-for cat, objs in selected_categorization.items():
-    colors = [
-        cat_colors[cat](x)
-        for x in np.linspace(COLOR_RANGE[0], COLOR_RANGE[1], len(selected_categorization[cat]))]
-    color_index = 0
-    for obj in objs:
-        objects[obj]['color'] = colors[color_index]
-        color_index += 1
-
-# Plot: histogramm
-fig = plt.figure(figsize=(25, 22))
-gs = gridspec.GridSpec(1, 1)
-gs.update(wspace=0.15, hspace=0.15)
-axes = []
-for elem in gs:
-    axes.append(fig.add_subplot(elem))
-axes[0].grid(axis='x', zorder=0)
-axes[0].set_xticks(range(0, 500, 50))
-sns.barplot(
-    x=list(v["count"] for o, v in objects.items() if o in selected_objects),
-    y=list(selected_objects),
-    ax=axes[0],
-    zorder=3,
-    palette=list(v["color"] for o, v in objects.items() if o in selected_objects))
-axes[0].set_xticklabels(axes[0].get_xticklabels(), rotation=90)
-plt.xticks(rotation=0, fontsize=FONTSIZE)
-plt.yticks(fontsize=FONTSIZE)
-plt.xlabel('# images', labelpad=30, fontsize=FONTSIZE)
-
-# Plot: pie chart
-right_inset_ax = fig.add_axes([.3, .1, .5, .5], facecolor='k')
-outer_colors = [c(0.5) for c in cat_colors.values()]
-labels = [word.replace(' ', '\n') for word in list(selected_categorization)]
-# Need to be orderd by category
-vals = []
-groups = {cat: 0 for cat in selected_categorization.keys()}
-inner_colors = []
-for cat, members in selected_categorization.items():
-    for _ in members:
-        vals.append(objects[_]["count"])
-        inner_colors.append(objects[_]["color"])
-        groups[cat] += objects[_]["count"]
-right_inset_ax.pie(
-    list(groups.values()),
-    radius=1,
-    colors=outer_colors,
-    #    labels=labels,
-    autopct='%.1f%%',
-    pctdistance=0.82,
-    #    labeldistance=1.5,
-    textprops={'color': 'white', 'fontsize': FONTSIZE},
-    wedgeprops={'width': PIE_INNER_RADIUS, 'edgecolor': 'w'})
-right_inset_ax.pie(
-    vals,
-    radius=1-PIE_INNER_RADIUS,
-    colors=inner_colors,
-    wedgeprops={'width': PIE_INNER_RADIUS, 'edgecolor': 'w'})
-
-# Plot: add legend and save
-plt.legend(
-    labels, bbox_to_anchor=(1.2, 1.45),
-    loc='upper right', prop={'size': 1.5*FONTSIZE})
-plt.savefig(OUTPUT)
-# plt.show()

hot_analysis/jc_graphs/plot_partwise_contacts.py

@@ -1,42 +0,0 @@
-import csv
-from pathlib import Path
-
-from matplotlib import gridspec
-from matplotlib import pyplot as plt
-import seaborn as sns
-
-# Input/output files
-CSV_FOLDER = Path(__file__).parent / "documents-export-2023-03-07"
-CONTACT_FILE = CSV_FOLDER / "partwise_contact_graph.csv"
-OUTPUT = 'output.pdf'
-
-# Some configuration
-FONTSIZE = 30
-plt.rcParams['grid.color'] = (0.5, 0.5, 0.5, 0.1)  # low grid opacity
-
-# Read CSV file
-body_parts = []
-body_part_counts = []
-with open(CONTACT_FILE, newline='', encoding="utf-8") as csvfile:
-    reader = csv.DictReader(csvfile)
-    for row in reader:
-        body_parts.append(row[''])
-        body_part_counts.append(int(row['count']))
-
-# Plot
-fig = plt.figure(figsize=(25, 22))
-gs = gridspec.GridSpec(1, 1)
-gs.update(wspace=0.15, hspace=0.15)
-axes = []
-for elem in gs:
-    axes.append(fig.add_subplot(elem))
-axes[0].grid(axis='y', zorder=0)
-sns.barplot(
-    x=body_parts, y=body_part_counts, ax=axes[0], zorder=3,
-    facecolor=(0.2, 0.4, 0.6, 0.6))
-axes[0].set_xticklabels(axes[0].get_xticklabels(), rotation=90)
-plt.xticks(rotation=45, ha='right', fontsize=FONTSIZE)
-plt.yticks(fontsize=FONTSIZE)
-plt.ylabel('# images', labelpad=30, fontsize=FONTSIZE)
-plt.savefig(OUTPUT)
-# plt.show()

hot_analysis/object_nest_piechart.py

@@ -1,136 +0,0 @@
-# make a nestest plotly pie chart given a list of labels and a list of values
-import os.path as osp
-import json
-import plotly.express as px
-import plotly.io as pio
-
-version = '1'
-dir = '/is/cluster/work/stripathi/pycharm_remote/dca_contact/hot_analysis/'
-out_dir_hico = osp.join(dir, f'filtered_data/v_{version}/hico')
-out_dir_vcoco = osp.join(dir, f'filtered_data/v_{version}/vcoco')
-
-objectwise_img_dict_hico = osp.join(out_dir_hico, 'imgnames_per_object_dict.json')
-objectwise_img_dict_vcoco = osp.join(out_dir_vcoco, 'imgnames_per_object_dict.json')
-
-with open(objectwise_img_dict_hico, 'r') as fp:
-    objectwise_img_dict_hico = json.load(fp)
-    # replace underscore with space
-    objectwise_img_dict_hico = {k.replace('_', ' '): v for k, v in objectwise_img_dict_hico.items()}
-    # replace values with lenght of values
-    objectwise_img_dict_hico = {k: len(v) for k, v in objectwise_img_dict_hico.items()}
-with open(objectwise_img_dict_vcoco, 'r') as fp:
-    objectwise_img_dict_vcoco = json.load(fp)
-    # replace underscore with space
-    objectwise_img_dict_vcoco = {k.replace('_', ' '): v for k, v in objectwise_img_dict_vcoco.items()}
-    # replace values with lenght of values
-    objectwise_img_dict_vcoco = {k: len(v) for k, v in objectwise_img_dict_vcoco.items()}
-
-# combine the dicts
-objectwise_img_dict = objectwise_img_dict_hico.copy()
-objectwise_img_dict.update(objectwise_img_dict_vcoco)
-
-
-categorization = {"transportation": ['motorcycle','bicycle','boat','car','truck','bus','train','airplane',],
-                  "accessories": ['backpack', 'tie', 'handbag', 'baseball glove'],
-                  "furniture": ['bench','chair','couch','bed','toilet','dining table'],
-                  'everyday objects': ['book','umbrella','cell phone','laptop','kite','suitcase','bottle','remote',
-                                       'toothbrush','teddy bear','scissors','keyboard','hair drier','traffic light',
-                                       'fire hydrant','stop sign','tv','vase','parking meter','clock','potted plant','mouse',],
-                  'sports equipment': ['frisbee','sports ball','tennis racket','baseball bat','skateboard','snowboard','skis','surfboard',],
-                  'food items': ['banana','cake','apple','carrot','pizza','donut','hot dog','sandwich','broccoli','orange'],
-                  'kitchen appliances': ['knife', 'spoon', 'cup', 'wine glass', 'oven', 'fork', 'bowl', 'refrigerator', 'toaster', 'sink', 'microwave',]}
-
-# get total lengths of each category
-objectwise_img_dict_categorized = {}
-for k, v in categorization.items():
-    objectwise_img_dict_categorized[k] = sum([objectwise_img_dict[obj] for obj in v])
-
-# reverse categorization
-categorization_rev = {}
-for k, v in categorization.items():
-    for obj in v:
-        categorization_rev[obj] = k
-
-
-
-data = dict(
-    character=list(categorization.keys()) + list(categorization_rev.keys()),
-    parent= ["objects"] * len(categorization.keys()) + list(categorization_rev.values()),
-    value =[0] * len(categorization.keys()) + list(objectwise_img_dict.values()),
-)
-
-# save data as pandas
-import pandas as pd
-df = pd.DataFrame(data)
-df.to_csv(osp.join(dir, 'object_nest_piechart_data.csv'))
-
-
-fig = px.sunburst(
-    data,
-    names='character',
-    parents='parent',
-    values='value',
-)
-
-# chage font size of the innermost level
-fig.update_traces(textfont_size=30)
-
-# save the figure
-out_path = osp.join(dir, "object_nest_piechart.html")
-fig.write_html(out_path)
-# Save plot as PNG wihtout transparent background
-out_path = osp.join(dir, "object_nest_piechart.png")
-fig.write_image(out_path,
-                format='png',
-                width=2000, height=1000, scale=1, engine='kaleido')
-
-
-# Set layout
-fig.update_layout(
-    margin=dict(t=0, l=0, r=0, b=0),
-    plot_bgcolor='rgba(0, 0, 0, 0)',
-    paper_bgcolor='rgba(0, 0, 0, 0)'
-)
-
-# Save plot as HTML with transparent background
-out_path = osp.join(dir, "object_nest_piechart_transparent.html")
-pio.write_html(fig, file=out_path, auto_open=False, include_plotlyjs='cdn', config=dict(displayModeBar=False))
-
-# Save plot as PNG with transparent background
-out_path = osp.join(dir, "object_nest_piechart_transparent.png")
-pio.write_image(fig, file=out_path,
-                format='png',
-                width=2000, height=1000, scale=1, engine='kaleido')
-
-import matplotlib.pyplot as plt
-import seaborn as sns
-
-# make a bar plot of objectwise_img_dict
-
-# sort the dict
-objectwise_img_dict = {k: v for k, v in sorted(objectwise_img_dict.items(), key=lambda item: item[1], reverse=True)}
-
-# save as pandas
-import pandas as pd
-df = pd.DataFrame.from_dict(objectwise_img_dict, orient='index', columns=['count'])
-df.to_csv(osp.join(dir, 'image_per_object_category.csv'))
-
-
-plt.figure(figsize=(20, 10))
-sns.barplot(x=list(objectwise_img_dict.keys()), y=list(objectwise_img_dict.values()))
-# make horizontal grid lines
-plt.grid(axis='y', alpha=0.5)
-
-# Add x-axis and y-axis labels
-plt.xticks(rotation=45, ha='right', fontsize=15)
-plt.yticks(fontsize=15)
-plt.show()
-# avoid clipping of x-axis labels
-plt.tight_layout()
-
-# save the figure
-out_path = osp.join(dir, "image_per_object_category.png")
-plt.savefig(out_path, transparent=False)
-out_path = osp.join(dir, "image_per_object_category_transparent.png")
-plt.savefig(out_path, transparent=True)
-

hot_analysis/partwise_contact_graph.py

@@ -1,98 +0,0 @@
-import numpy as np
-import os
-import json
-import os.path as osp
-
-
-# Load the combined dca train, val and test npzs
-dir = '/is/cluster/work/stripathi/pycharm_remote/dca_contact/data/dataset_extras'
-trainval_npz = np.load(os.path.join(dir, 'hot_dca_trainval.npz'), allow_pickle=True)
-test_npz = np.load(os.path.join(dir, 'hot_dca_test.npz'), allow_pickle=True)
-
-# combine the two npz
-combined_npz = {}
-for key in trainval_npz.keys():
-    combined_npz[key] = np.concatenate([trainval_npz[key], test_npz[key]], axis=0)
-
-segmentation_path = 'data/smpl_vert_segmentation.json'
-with open(segmentation_path, 'rb') as f:
-    part_segmentation = json.load(f)
-
-# reverse the part segmentation
-part_segmentation_rev = {}
-for part in part_segmentation:
-    for vert in part_segmentation[part]:
-        part_segmentation_rev[vert] = part
-
-part_names_combined = []
-for cls in combined_npz['contact_label']:
-    cls_idx = np.where(cls == 1)[0]
-    part_names = [part_segmentation_rev[vert] for vert in cls_idx]
-    # find count for every part in part_names
-    part_count = {}
-    for part in part_names:
-        if part not in part_count:
-            part_count[part] = 0
-        part_count[part] += 1
-    # find the parts with count > 10
-    part_names = [part for part in part_count if part_count[part] > 10]
-    part_names_combined.append(part_names)
-
-# make a histogram of the part names
-part_names_combined = [item for sublist in part_names_combined for item in sublist]
-part_names_combined = np.array(part_names_combined)
-unique, counts = np.unique(part_names_combined, return_counts=True)
-part_names_combined = dict(zip(unique, counts))
-
-print('Total number of parts: ', len(part_names_combined))
-print(part_names_combined.keys())
-# set keys to combine;
-combine_keys = {'leftFoot': ['leftToeBase'],
-                'rightFoot': ['rightToeBase'],
-                'leftHand': ['leftHandIndex1'],
-                'rightHand': ['rightHandIndex1'],
-                'spine': ['spine1', 'spine2'],
-                'head': ['neck'],}
-
-for key in combine_keys:
-    for subkey in combine_keys[key]:
-        part_names_combined[key] += part_names_combined[subkey]
-        del part_names_combined[subkey]
-
-print('Total number of parts: ', len(part_names_combined))
-
-# sort the dictionary
-part_names_combined = {k: v for k, v in sorted(part_names_combined.items(), key=lambda item: item[1], reverse=True)}
-
-# convert to pandas
-import pandas as pd
-df = pd.DataFrame.from_dict(part_names_combined, orient='index', columns=['count'])
-df.to_csv(osp.join(dir, 'partwise_contact_graph.csv'))
-
-
-
-# make a beautiful bar plot using seabord and change the default color palette
-import seaborn as sns
-import matplotlib.pyplot as plt
-
-# set the color palette
-
-# make the plot
-fig, ax = plt.subplots(figsize=(20, 10))
-sns.barplot(x=list(part_names_combined.keys()), y=list(part_names_combined.values()), ax=ax,
-            palette=sns.color_palette("rocket", len(part_names_combined)))
-ax.set_xticklabels(ax.get_xticklabels(), rotation=90)
-plt.xticks(rotation=45, ha='right', fontsize=30)
-plt.yticks(fontsize=30)
-# avoid clipping of xtick labels
-plt.tight_layout()
-
-
-
-# save the plot
-outdir = "/is/cluster/work/stripathi/pycharm_remote/dca_contact/hot_analysis"
-out_path = os.path.join(outdir, "partwise_contact_graph.png")
-plt.savefig(out_path, transparent=True, dpi=300)
-
-
-

hot_analysis/vcoco_analysis.ipynb

@@ -1,276 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import json\n",
-    "import pandas as pd \n",
-    "import ipdb\n",
-    "import os\n",
-    "import pickle as pkl\n",
-    "import os.path as osp\n",
-    "import numpy as np\n",
-    "from PIL import Image"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Total images found: 5459\n",
-      "Images after KP filtering: 2386\n",
-      "['vcoco_000000051899.jpg', 'vcoco_000000093127.jpg', 'vcoco_000000455665.jpg', 'vcoco_000000248389.jpg', 'vcoco_000000403947.jpg']\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Load Agniv VITpose-base hot dict\n",
-    "filter_path = \"./agniv_pose_filter/hot_dict.pkl\"\n",
-    "with open(filter_path, 'rb') as f:\n",
-    "    pose_md_dict = pkl.load(f)\n",
-    "    \n",
-    "vcoco_dict = {}\n",
-    "\n",
-    "for k, v in pose_md_dict.items():\n",
-    "    if 'vcoco' in k:\n",
-    "        vcoco_dict[k] = v\n",
-    "    \n",
-    "print(f'Total images found: {len(vcoco_dict)}')\n",
-    "\n",
-    "# Filter out images with < 10 visible keypoints \n",
-    "kp_thresh = 10\n",
-    "\n",
-    "filter_img_names = {}\n",
-    "\n",
-    "for imgname, kp_md in vcoco_dict.items():\n",
-    "    if kp_md == 0:\n",
-    "        continue\n",
-    "    if kp_md[\"num_persons\"] == 1 and kp_md[\"num_kpt\"][0.5][0] > kp_thresh:\n",
-    "        filter_img_names[imgname] = kp_md[\"num_kpt\"][0.5][0]\n",
-    "        \n",
-    "print(f'Images after KP filtering: {len(filter_img_names)}')\n",
-    "\n",
-    "print(list(filter_img_names.keys())[:5])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 35,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "loading annotations into memory...\n",
-      "Done (t=1.30s)\n",
-      "creating index...\n",
-      "index created!\n",
-      "Final number of images 2368\n"
-     ]
-    }
-   ],
-   "source": [
-    "from pycocotools.coco import COCO\n",
-    "version = '1'\n",
-    "out_dir = f'./filtered_data/v_{version}/vcoco'\n",
-    "os.makedirs(out_dir, exist_ok=True)\n",
-    "\n",
-    "coco_dir = '/is/cluster/work/stripathi/pycharm_remote/v-coco/data'\n",
-    "coco = COCO(os.path.join(coco_dir, 'instances_vcoco_all_2014.json'))\n",
-    "\n",
-    "imgwise_object_names = {}\n",
-    "img_dir = '/ps/project/datasets/HOT/Contact_Data/images/training/'\n",
-    "\n",
-    "bad_object_names = ['bird', 'cat', 'dog', 'horse', 'sheep', 'cow', \n",
-    "                    'elephant', 'bear', 'zebra', 'giraffe']\n",
-    "\n",
-    "# # Get all coco objects\n",
-    "# count = 0\n",
-    "# for id in range(91):\n",
-    "#     try: \n",
-    "#         print(coco.loadCats(id))\n",
-    "#         count += 1\n",
-    "#     except:\n",
-    "#         print(f'ID:{id} does not exist')\n",
-    "#         continue\n",
-    "# print(count)\n",
-    "\n",
-    "objectwise_img_names = {}\n",
-    "for img_name in filter_img_names.keys():\n",
-    "    img_id = int(os.path.splitext(img_name.split('_')[-1])[0])\n",
-    "    ann_ids = coco.getAnnIds([img_id])\n",
-    "    anns = coco.loadAnns(ann_ids)\n",
-    "    object_list = []\n",
-    "    for ann in anns:\n",
-    "        object_cat = coco.loadCats(ann[\"category_id\"])\n",
-    "        if len(object_cat) > 1:\n",
-    "            ipdb.set_trace()\n",
-    "        object_name = object_cat[0]['name']\n",
-    "        if object_name in bad_object_names:\n",
-    "            continue\n",
-    "        if object_name != 'person':\n",
-    "            object_list.append(object_name)\n",
-    "    if len(object_list) != 0:\n",
-    "        imgwise_object_names[img_name] = list(set(object_list))\n",
-    "        \n",
-    "    for obj_name in set(object_list):\n",
-    "        objectwise_img_names.setdefault(obj_name,[]).append(img_name)\n",
-    "        \n",
-    "#         # Visualize images \n",
-    "#         print(img_name)\n",
-    "#         print(list(set(object_list)))\n",
-    "#         img = Image.open(osp.join(img_dir,img_name))\n",
-    "#         display(img)\n",
-    "    \n",
-    "    \n",
-    "print(f'Final number of images {len(imgwise_object_names)}')\n",
-    "    \n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 36,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "saved at ./filtered_data/v_1/vcoco/object_per_image_dict.json\n",
-      "saved at ./filtered_data/v_1/vcoco/vcoco_imglist_all_170223.txt\n",
-      "saved at ./filtered_data/v_1/vcoco/imgnames_per_object_dict.json\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Save the imagewise_object dict\n",
-    "out_path = osp.join(out_dir, 'object_per_image_dict.json')\n",
-    "with open(out_path, 'w') as fp:\n",
-    "    json.dump(imgwise_object_names, fp)\n",
-    "    print(f'saved at {out_path}')\n",
-    "    \n",
-    "# save image_list \n",
-    "out_path = osp.join(out_dir, 'vcoco_imglist_all_170223.txt')\n",
-    "with open(out_path, 'w') as f:\n",
-    "    f.write('\\n'.join(imgwise_object_names.keys()))\n",
-    "    print(f'saved at {out_path}')\n",
-    "\n",
-    "\n",
-    "# Save the object_wise dict\n",
-    "out_path = osp.join(out_dir, 'imgnames_per_object_dict.json')\n",
-    "with open(out_path, 'w') as fp:\n",
-    "    json.dump(objectwise_img_names, fp)\n",
-    "    print(f'saved at {out_path}')\n",
-    "\n",
-    "    \n",
-    "\n",
-    "    "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "5072\n"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 432x288 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns\n",
-    "\n",
-    "# sort the dictionary \n",
-    "objectwise_img_names = dict(sorted(objectwise_img_names.items(), key=lambda x: len(x[1]), reverse=True))\n",
-    "\n",
-    "# Extract object names and image counts\n",
-    "obj_names = list(objectwise_img_names.keys())\n",
-    "img_counts = [len(objectwise_img_names[obj]) for obj in objectwise_img_names]\n",
-    "print(sum(img_counts))\n",
-    "\n",
-    "# Create bar plot\n",
-    "sns.barplot(x=obj_names, y=img_counts)\n",
-    "\n",
-    "# Add x-axis and y-axis labels\n",
-    "plt.xlabel('Object')\n",
-    "plt.ylabel('Number of Images')\n",
-    "\n",
-    "plt.xticks(rotation=45, ha='right', fontsize=3)\n",
-    "\n",
-    "# Save the plot as a high-resolution image file\n",
-    "out_path = osp.join(out_dir, 'image_per_object_category.png')\n",
-    "plt.savefig(out_path, dpi=300)\n",
-    "\n",
-    "# Show plot\n",
-    "plt.show()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "    "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

scripts/datascripts/add_imgname_column_to_deco_csv.py

@@ -1,23 +0,0 @@
-#python scripts/datascripts/add_imgname_column_to_deco_csv.py --csv_path /ps/scratch/ps_shared/stripathi/deco/4agniv/DCA/mturk_csvs_combined_temp.csv --out_path /ps/scratch/ps_shared/stripathi/deco/4agniv/DCA/mturk_csvs_combined_temp_with_imgnames.csv
-
-import argparse
-import pandas as pd
-import os
-
-def add_imagename_column(csv_path, out_path):
-    # Load csv
-    csv_data = pd.read_csv(csv_path)
-
-    # Add column with image name from vertices column, where every element is a dictionary with key the image names as keys and values as the vertices
-    csv_data['imgnames'] = csv_data['vertices'].apply(lambda x: os.path.basename(list(eval(x).keys())[0]))
-
-    # Write combined data to new CSV file
-    csv_data.to_csv(out_path, index=False)
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--csv_path', type=str, default='/ps/scratch/ps_shared/stripathi/deco/4agniv/hot/dca.csv')
-    parser.add_argument('--out_path', type=str, default='/ps/scratch/ps_shared/stripathi/deco/4agniv/hot/dca_with_imgname.csv')
-    args = parser.parse_args()
-    add_imagename_column(args.csv_path, args.out_path)
-

scripts/datascripts/combine_cropped_npz.py

@@ -1,63 +0,0 @@
-'''
-Combine cropped npz given a folder of npz
-'''
-
-import argparse
-import os
-import numpy as np
-
-def combine_npz(npz_dir, out_npz):
-    # get all npz files in the folder
-
-    npz_files = [os.path.join(npz_dir, out_dir, f) for f in os.listdir(npz_dir, out_dir) if f.endswith('.npz')]
-    print('Found {} npz files'.format(len(npz_files)))
-
-    # combine all the values in all keys in all npz files
-    c_imgname = []
-    c_pose = []
-    c_transl = []
-    c_shape = []
-    c_cam_k = []
-    c_contact_label = []
-    c_scene_seg = []
-    c_part_seg = []
-
-    for npz_file in npz_files:
-        npz= np.load(npz_file)
-        c_imgname.extend(npz['imgname'])
-        c_pose.extend(npz['pose'])
-        c_transl.extend(npz['transl'])
-        c_shape.extend(npz['shape'])
-        c_cam_k.extend(npz['cam_k'])
-        c_contact_label.extend(npz['contact_label'])
-        c_scene_seg.extend(npz['scene_seg'])
-        c_part_seg.extend(npz['part_seg'])
-
-    # convert to numpy arrays
-    c_imgname = np.concatenate(c_imgname, axis=0)
-    c_pose = np.concatenate(c_pose, axis=0)
-    c_transl = np.concatenate(c_transl, axis=0)
-    c_shape = np.concatenate(c_shape, axis=0)
-    c_cam_k = np.concatenate(c_cam_k, axis=0)
-    c_contact_label = np.concatenate(c_contact_label, axis=0)
-    c_scene_seg = np.concatenate(c_scene_seg, axis=0)
-    c_part_seg = np.concatenate(c_part_seg, axis=0)
-
-    # save the new npz
-    np.savez(out_npz,
-                imgname=c_imgname,
-                pose=c_pose,
-                transl=c_transl,
-                shape=c_shape,
-                cam_k=c_cam_k,
-                contact_label=c_contact_label,
-                scene_seg=c_scene_seg,
-                part_seg=c_part_seg)
-    print('Saved combined npz to {}'.format(out_npz))
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--orig_npz_dir', type=str, default='/is/cluster/fast/achatterjee/rich/scene_npzs/train')
-    parser.add_argument('--out_npz', type=str, required=True,default='/is/cluster/fast/achatterjee/rich/scene_npzs/train_combined.npz')
-    args = parser.parse_args()
-    combine_npz(npz_dir = args.orig_npz_dir, out_npz = args.out_npz)

scripts/datascripts/combine_mturk_csvs.py

@@ -1,33 +0,0 @@
-# write a script to find all csvs in a folder and merge them
-
-import os
-import pandas as pd
-import argparse
-
-def combine_csvs(folder_path, out_path):
-    # Create empty DataFrame to store combined data
-    combined_data = pd.DataFrame()
-
-    # Loop through all files in folder with .csv extension
-    for file in os.listdir(folder_path):
-        if file.endswith(".csv"):
-            file_path = os.path.join(folder_path, file)
-            # Read CSV file and append to combined_data
-            csv_data = pd.read_csv(file_path)
-            combined_data = combined_data.append(csv_data, ignore_index=True)
-
-    # Write combined data to new CSV file
-    combined_data.to_csv(out_path, index=False)
-    print(f"Combined CSV file saved to {out_path}")
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--folder_path', type=str, default='/ps/scratch/ps_shared/stripathi/deco/4agniv/hot/')
-    parser.add_argument('--out_path', type=str, default='/ps/scratch/ps_shared/stripathi/deco/4agniv/hot/combined.csv')
-    args = parser.parse_args()
-    folder_path = args.folder_path
-    out_path = args.out_path
-    combine_csvs(folder_path, out_path)
-
-
-

scripts/datascripts/combine_npzs.py

@@ -1,41 +0,0 @@
-'''
-Combine the npzs
-'''
-
-import numpy as np
-
-d1 = np.load('/is/cluster/work/stripathi/pycharm_remote/dca_contact/data/dataset_extras/hot_noprox_supporting_False_trainval_0.npz',allow_pickle=True)
-d2 = np.load('/is/cluster/work/stripathi/pycharm_remote/dca_contact/data/dataset_extras/hot_noprox_supporting_False_trainval_1.npz',allow_pickle=True)
-d3 = np.load('/is/cluster/work/stripathi/pycharm_remote/dca_contact/data/dataset_extras/hot_noprox_supporting_False_trainval_2.npz',allow_pickle=True)
-d4 = np.load('/is/cluster/work/stripathi/pycharm_remote/dca_contact/data/dataset_extras/hot_noprox_supporting_False_trainval_3.npz',allow_pickle=True)
-
-
-print(list(d1.keys()))
-print(type(d1['imgname']))
-print(d1['imgname'].shape)
-
-c_imgname = np.concatenate((d1['imgname'], d2['imgname'], d3['imgname'], d4['imgname']), axis=0)
-c_pose = np.concatenate((d1['pose'], d2['pose'], d3['pose'], d4['pose']), axis=0)
-c_transl = np.concatenate((d1['transl'], d2['transl'], d3['transl'], d4['transl']), axis=0)
-c_shape = np.concatenate((d1['shape'], d2['shape'], d3['shape'], d4['shape']), axis=0)
-c_cam_k = np.concatenate((d1['cam_k'], d2['cam_k'], d3['cam_k'], d4['cam_k']), axis=0)
-c_polygon_2d_contact = np.concatenate((d1['polygon_2d_contact'], d2['polygon_2d_contact'],
-                                       d3['polygon_2d_contact'], d4['polygon_2d_contact']), axis=0)
-c_contact_label = np.concatenate((d1['contact_label'], d2['contact_label'], d3['contact_label'],
-                                  d4['contact_label']), axis=0)
-c_scene_seg = np.concatenate((d1['scene_seg'], d2['scene_seg'], d3['scene_seg'], d4['scene_seg']), axis=0)
-c_part_seg = np.concatenate((d1['part_seg'], d2['part_seg'], d3['part_seg'], d4['part_seg']), axis=0)
-
-outfile = '/is/cluster/work/stripathi/pycharm_remote/dca_contact/data/dataset_extras/hot_noprox_supporting_False_trainval_combined.npz'
-np.savez(outfile,
-         imgname=c_imgname,
-         pose=c_pose,
-         transl=c_transl,
-         shape=c_shape,
-         cam_k=c_cam_k,
-         polygon_2d_contact=c_polygon_2d_contact,
-         contact_label=c_contact_label,
-         scene_seg=c_scene_seg,
-         part_seg=c_part_seg
-        )
-print(f'Saved to {outfile}')

scripts/datascripts/convert_rich_npz_to_cropped.py

@@ -1,75 +0,0 @@
-'''
-Fix paths  to cropped images, partmasks and segmasks
-'''
-
-import argparse
-import os
-import numpy as np
-from tqdm import tqdm
-
-def convert_rich_npz(orig_npz, out_dir):
-    # go through all keys in the npz
-    # if the key is imgname, partmask or segmask, replace the path with the new path
-    # save the new npz
-
-    # structs we use
-    imgnames_ = []
-    poses_, shapes_, transls_ = [], [], []
-    cams_k_ = []
-    contact_label_ = []
-    scene_seg_, part_seg_ = [], []
-
-    # load the npz
-    npz = np.load(orig_npz)
-    for i in tqdm(range(len(npz['imgname']))):
-
-        if not os.path.exists(npz['imgname'][i]):
-            print(npz['imgname'][i])
-            continue
-
-        new_scene_seg = os.path.exists(npz['scene_seg'][i].replace('seg_masks_new', 'segmentation_masks'))
-
-        if not new_scene_seg:
-            print(new_scene_seg)
-            continue
-
-        if not os.path.exists(npz['part_seg'][i]):
-            print(npz['part_seg'][i])
-            continue
-
-        imgnames_.append(npz['imgname'][i])
-        poses_.append(npz['pose'][i])
-        transls_.append(npz['transl'][i])
-        shapes_.append(npz['shape'][i])
-        cams_k_.append(npz['cam_k'][i])
-        contact_label_.append(npz['contact_label'][i])
-        scene_seg_.append(npz['scene_seg'][i].replace('seg_masks_new', 'segmentation_masks'))
-        part_seg_.append(npz['part_seg'][i])
-
-    # save the new npz
-    out_dir = out_dir+'_cropped'
-    os.makedirs(out_dir, exist_ok=True)
-    out_file = os.path.join(out_dir, os.path.basename(args.orig_npz))
-    np.savez(out_file,
-             imgname=imgnames_,
-             pose=poses_,
-             transl=transls_,
-             shape=shapes_,
-             cam_k=cams_k_,
-             contact_label=contact_label_,
-             scene_seg=scene_seg_,
-             part_seg=part_seg_)
-
-    print('Saved to: ', out_file)
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--orig_npz_dir', type=str, default='/is/cluster/fast/achatterjee/rich/scene_npzs/train')
-    parser.add_argument('--cluster_idx', type=int)
-    args = parser.parse_args()
-    # get all npz files in the directory
-    npz_files = [os.path.join(args.orig_npz_dir, f) for f in os.listdir(args.orig_npz_dir) if f.endswith('.npz')]
-    # get the npz file for this cluster
-    orig_npz = npz_files[args.cluster_idx]
-    convert_rich_npz(orig_npz, out_dir=args.orig_npz_dir)

scripts/datascripts/get_part_seg_mask.py

@@ -1,199 +0,0 @@
-# python scripts/datascripts/get_part_seg_mask.py --data_npz data/rich_val_smplx_small.npz --model_type 'smplx'
-
-
-import os
-import sys
-sys.path.append('/is/cluster/work/achatterjee/dca_contact')
-import cv2
-import argparse
-import numpy as np
-import torch
-from common import constants
-from models.smpl import SMPL
-from smplx import SMPLX
-from utils.mesh_utils import save_results_mesh
-import trimesh
-from tqdm import tqdm
-from utils.image_utils import get_body_part_texture, generate_part_labels
-from utils.diff_renderer import Pytorch3D
-
-class PART_LABELER:
-    def __init__(self, body_params, img_w, img_h, model_type, debug=False):
-        """
-        Get part segmentation masks for images
-
-        Args:
-            body_params: SMPL parameters
-            img_w: image width
-            img_h: image height
-            model_type: 'smpl' or 'smplx'
-        """
-        self.device = torch.device('cuda:{}'.format(args.gpu)) if torch.cuda.is_available() else torch.device('cpu')
-
-        self.model_type = model_type
-
-        # Setup the SMPL model
-        if self.model_type == 'smpl':
-            self.body_model = SMPL(constants.SMPL_MODEL_DIR).to(self.device)
-        if self.model_type == 'smplx':
-            self.body_model = SMPLX(constants.SMPL_MODEL_DIR,
-                                    num_betas=10,
-                                    use_pca=False).to(self.device)
-
-        self.body_part_vertex_colors, self.body_part_texture = get_body_part_texture(self.body_model.faces,
-                                                                                     model_type=self.model_type,
-                                                                                     non_parametric=False)
-        # bins are discrete part labels, add eps to avoid quantization error
-        eps = 1e-2
-        # self.part_label_bins = (torch.arange(int(constants.N_PARTS)) / float(constants.N_PARTS)) + eps
-        self.part_label_bins = torch.linspace(0, constants.N_PARTS-1, constants.N_PARTS) + eps
-
-        ## Run SMPL forward
-        self.body_params = body_params
-
-        self.smpl_verts, self.smpl_joints = self.get_posed_mesh(debug)
-
-        # Assumbe same focal lenght for all frames in a seq
-        focal_length = self.body_params['cam_k'][0, 0, 0]
-        # focal_length = focal_length[0]
-        # Setup Pyrender renderer
-        # self.renderer = Renderer(focal_length=focal_length, img_w=img_w, img_h=img_h,
-        #                          faces=self.smpl_model.faces,
-        #                          same_mesh_color=False)
-
-        # Setup Pytorch3D Renderer
-        focal_length = torch.FloatTensor([focal_length])
-        smpl_faces = torch.from_numpy(self.body_model.faces.astype(np.int32)).to(self.device)
-        self.renderer = Pytorch3D(img_h=img_h,
-                                  img_w=img_w,
-                                  focal_length=focal_length,
-                                  smpl_faces=smpl_faces,
-                                  texture_mode='partseg',
-                                  vertex_colors=self.body_part_vertex_colors,
-                                  face_textures=self.body_part_texture,
-                                  model_type=self.model_type)
-
-    def get_posed_mesh(self, debug=False):
-        betas = torch.from_numpy(self.body_params['shape']).float().to(self.device)
-        pose = torch.from_numpy(self.body_params['pose']).float().to(self.device)
-        transl = torch.from_numpy(self.body_params['transl']).float().to(self.device)
-
-        # extra smplx params
-        extra_args = {'jaw_pose': torch.zeros((betas.shape[0], 3)).float().to(self.device),
-                        'leye_pose': torch.zeros((betas.shape[0], 3)).float().to(self.device),
-                        'reye_pose': torch.zeros((betas.shape[0], 3)).float().to(self.device),
-                        'expression': torch.zeros((betas.shape[0], 10)).float().to(self.device),
-                        'left_hand_pose': torch.zeros((betas.shape[0], 45)).float().to(self.device),
-                        'right_hand_pose': torch.zeros((betas.shape[0], 45)).float().to(self.device)}
-
-        smpl_output = self.body_model(betas=betas,
-                                      body_pose=pose[:, 3:],
-                                      global_orient=pose[:, :3],
-                                      pose2rot=True,
-                                      transl=transl,
-                                      **extra_args)
-        smpl_verts = smpl_output.vertices.detach().cpu().numpy()
-        smpl_joints = smpl_output.joints.detach().cpu().numpy()
-
-        if debug:
-            for mesh_i in range(smpl_verts.shape[0]):
-                out_dir = 'temp_meshes'
-                os.makedirs(out_dir, exist_ok=True)
-                out_file = os.path.join(out_dir, f'temp_mesh_{mesh_i:04d}.obj')
-                save_results_mesh(smpl_verts[mesh_i], self.body_model.faces, out_file)
-        return smpl_verts, smpl_joints
-
-    def bucketize_part_image(self, color_rgb, mask):
-        # make single channel
-        body_parts = color_rgb.clone()
-        body_parts *= 255.  # multiply it with 255 to make labels distant
-        body_parts = body_parts.max(-1)[0]  # reduce to single channel
-        body_parts = torch.bucketize(body_parts, self.part_label_bins, right=True)  # np.digitize(body_parts, bins, right=True)
-        # add 1 to make background label 0
-        body_parts = body_parts.long() + 1
-        body_parts = body_parts * mask.detach()
-        return body_parts.long()
-
-    def create_part_masks(self, body_parts):
-        # extract every pixel as a separate mask
-        part_masks = []
-        for part_id in range(1, constants.N_PARTS+1): # first one is for background
-            part_mask = (body_parts == part_id)
-            part_masks.append(part_mask)
-        return part_masks
-
-    def render_part_mask_p3d(self, img_paths, out_dir):
-        with torch.no_grad():
-            # os.makedirs(out_dir, exist_ok=True)
-            for index, img_path in tqdm(enumerate(img_paths), dynamic_ncols=True):
-                # Load the image
-                if not os.path.exists(img_path):
-                    if 'train' in img_path:
-                        split = 'train'
-                    elif 'val' in img_path:
-                        split = 'val'
-                    else:
-                        split = 'test'        
-                    new_img_name = img_path[img_path.index(split)+4:].replace('/', '_')
-                    new_path = os.path.join('/is/cluster/work/achatterjee/rich/images', split, new_img_name.replace('jpeg', 'bmp'))
-                    if not os.path.exists(new_path):
-                        new_path = new_path.replace('bmp', 'png')
-                    img_path = new_path    
-                if os.path.exists(out_dir[index]):
-                    continue 
-                # img_bgr = cv2.imread(img_path)
-                chosen_vert_arr = torch.FloatTensor(self.smpl_verts[[index]]).to(self.device)
-                front_view = self.renderer(chosen_vert_arr)
-                front_view_rgb = front_view[0, :3, :, :].permute(1,2,0).detach().cpu()
-                front_view_mask = front_view[0, 3, :, :].detach().cpu()
-                # front_view_depth = front_view[0, 4, :, :].detach().cpu()
-
-                body_parts = self.bucketize_part_image(front_view_rgb, front_view_mask)
-                body_parts = body_parts.numpy()
-                front_view_rgb = front_view_rgb.numpy()
-
-                # body_part_masks = self.create_part_masks(body_parts)
-                # display part masks
-                # for part_id, part_mask in enumerate(body_part_masks):
-                #     part_mask = part_mask * 255
-                #     part_dir = os.path.join(out_dir, f'frame_{index:04d}_parts')
-                #     os.makedirs(part_dir, exist_ok=True)
-                #     out_file = os.path.join(part_dir, f'part_{part_id:02d}_{index:04d}.png')
-                #     cv2.imwrite(out_file, part_mask)
-
-                # out_file = os.path.join(out_dir, f'front_view_{index:04d}.png')
-                # cv2.imwrite(out_file, front_view_rgb[: ,:, [2, 1, 0]]*255)
-                # print(f'wrote front view to {out_file}')
-                body_parts = cv2.merge((body_parts, body_parts, body_parts))
-                # out_file = os.path.join(out_dir, f'body_parts_{index:04d}.png')
-                out_file = out_dir[index]
-                cv2.imwrite(out_file, body_parts)
-                # print(f'wrote body part masks to {out_file}')
-
-
-def main(args):
-    out_dir = args.out_dir
-    data_md = np.load(args.data_npz)
-
-    # get all the jpg files in the folder
-    img_paths = data_md['imgname']
-    seg_paths = data_md['part_seg']
-    print(f'found {len(img_paths)} images')
-    # load first image
-    img = cv2.imread(img_paths[0])
-    img_h, img_w, _ = img.shape
-
-    labeler = PART_LABELER(body_params=data_md, img_w=img_w, img_h=img_h,
-                           model_type=args.model_type, debug=args.debug)
-    labeler.render_part_mask_p3d(img_paths=img_paths, out_dir=seg_paths)
-
-if __name__=='__main__':
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--out_dir', type=str, default='./temp_part_masks/', help='image folder')
-    parser.add_argument('--data_npz', type=str, default='.', help='folder with smpl/smpl-x npz')
-    parser.add_argument('--model_type', type=str, default='smplx', choices=['smpl', 'smplx'], help='model type')
-    parser.add_argument('--gpu', type=int, default=0, help='gpu id')
-    parser.add_argument('--debug', action='store_true', help='debug mode', default=False)
-    args = parser.parse_args()
-
-    main(args)