retrrain on 30090

.github/workflows/main.yml

@@ -0,0 +1,21 @@
+name: Sync to Hugging Face hub
+on:
+  push:
+    branches: [main]
+
+  # to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+
+        
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: 0
+      - name: Push to hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: git push --force https://dnth:$HF_TOKEN@huggingface.co/spaces/dnth/webdemo-fridge-detection main

README.md

@@ -0,0 +1,37 @@
+---
+title: webdemo-fridge-detection
+emoji: 🍿
+colorFrom: red
+colorTo: purple
+sdk: gradio
+app_file: app.py
+pinned: false
+---
+
+# Configuration
+
+`title`: _string_  
+Display title for the Space
+
+`emoji`: _string_  
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_  
+Can be either `gradio` or `streamlit`
+
+`sdk_version` : _string_  
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_  
+Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
+Path is relative to the root of the repository.
+
+`pinned`: _boolean_  
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,73 @@
+from icevision.all import *
+import icedata
+import PIL, requests
+import torch
+from torchvision import transforms
+import gradio as gr
+
+# Download the dataset
+url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjects.zip"
+dest_dir = "fridge"
+data_dir = icedata.load_data(url, dest_dir)
+
+# Create the parser
+parser = parsers.VOCBBoxParser(annotations_dir=data_dir / "odFridgeObjects/annotations", images_dir=data_dir / "odFridgeObjects/images")
+
+# Parse annotations to create records
+train_records, valid_records = parser.parse()
+
+class_map = parser.class_map
+
+extra_args = {}
+model_type = models.torchvision.retinanet
+backbone = model_type.backbones.resnet50_fpn
+# Instantiate the model
+model = model_type.model(backbone=backbone(pretrained=True), num_classes=len(parser.class_map), **extra_args) 
+
+# Transforms
+# size is set to 384 because EfficientDet requires its inputs to be divisible by 128
+image_size = 384
+train_tfms = tfms.A.Adapter([*tfms.A.aug_tfms(size=image_size, presize=512), tfms.A.Normalize()])
+valid_tfms = tfms.A.Adapter([*tfms.A.resize_and_pad(image_size), tfms.A.Normalize()])
+# Datasets
+train_ds = Dataset(train_records, train_tfms)
+valid_ds = Dataset(valid_records, valid_tfms)
+# Data Loaders
+train_dl = model_type.train_dl(train_ds, batch_size=8, num_workers=4, shuffle=True)
+valid_dl = model_type.valid_dl(valid_ds, batch_size=8, num_workers=4, shuffle=False)
+metrics = [COCOMetric(metric_type=COCOMetricType.bbox)]
+learn = model_type.fastai.learner(dls=[train_dl, valid_dl], model=model, metrics=metrics)
+
+learn = learn.load('model')
+
+def show_preds(input_image, display_label, display_bbox, detection_threshold):
+
+    if detection_threshold==0: detection_threshold=0.5
+
+    img = PIL.Image.fromarray(input_image, 'RGB')
+
+    pred_dict  = model_type.end2end_detect(img, valid_tfms, model, class_map=class_map, detection_threshold=detection_threshold,
+                                           display_label=display_label, display_bbox=display_bbox, return_img=True, 
+                                           font_size=16, label_color="#FF59D6")
+
+    return pred_dict['img']
+
+# display_chkbox = gr.inputs.CheckboxGroup(["Label", "BBox"], label="Display", default=True)
+display_chkbox_label = gr.inputs.Checkbox(label="Label", default=True)
+display_chkbox_box = gr.inputs.Checkbox(label="Box", default=True)
+
+detection_threshold_slider = gr.inputs.Slider(minimum=0, maximum=1, step=0.1, default=0.5, label="Detection Threshold")
+
+outputs = gr.outputs.Image(type="pil")
+
+# Option 1: Get an image from local drive
+gr_interface = gr.Interface(fn=show_preds, inputs=["image", display_chkbox_label, display_chkbox_box,  detection_threshold_slider], outputs=outputs, title='IceApp - Fridge Object')
+
+# #  Option 2: Grab an image from a webcam
+# gr_interface = gr.Interface(fn=show_preds, inputs=["webcam", display_chkbox_label, display_chkbox_box,  detection_threshold_slider], outputs=outputs, title='IceApp - COCO', live=False)
+
+# #  Option 3: Continuous image stream from the webcam
+# gr_interface = gr.Interface(fn=show_preds, inputs=["webcam", display_chkbox_label, display_chkbox_box,  detection_threshold_slider], outputs=outputs, title='IceApp - COCO', live=True)
+
+
+gr_interface.launch(inline=False, share=True, debug=True)

gradioapp.ipynb

@@ -0,0 +1,262 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "ee7e0c23-3fa5-4547-8598-7df27a3876c5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from icevision.all import *\n",
+    "import icedata\n",
+    "import PIL, requests\n",
+    "import torch\n",
+    "from torchvision import transforms\n",
+    "import gradio as gr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "646cc218-f7de-4f32-a3d9-fccdc9b54592",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Download the dataset\n",
+    "url = \"https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjects.zip\"\n",
+    "dest_dir = \"fridge\"\n",
+    "data_dir = icedata.load_data(url, dest_dir)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "96184ca0-0b0a-4a20-8ab9-30dee6096588",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create the parser\n",
+    "parser = parsers.VOCBBoxParser(annotations_dir=data_dir / \"odFridgeObjects/annotations\", images_dir=data_dir / \"odFridgeObjects/images\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "dfa20f76-4970-479a-9497-871fe4cfd170",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "fc8e676815314038a40c884c8c7f5b67",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/128 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m\u001b[1mINFO    \u001b[0m\u001b[1m\u001b[0m - \u001b[1m\u001b[34m\u001b[1mAutofixing records\u001b[0m\u001b[1m\u001b[34m\u001b[0m\u001b[1m\u001b[0m | \u001b[36micevision.parsers.parser\u001b[0m:\u001b[36mparse\u001b[0m:\u001b[36m122\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3db4bc1ae388495eb3b62289459a5c00",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/128 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<ClassMap: {'background': 0, 'carton': 1, 'milk_bottle': 2, 'can': 3, 'water_bottle': 4}>"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Parse annotations to create records\n",
+    "train_records, valid_records = parser.parse()\n",
+    "parser.class_map"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "26d4f2f7-db51-413c-838f-f80c5898ab52",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class_map = parser.class_map"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "007b2e97-d546-4178-84e7-d4fe597f3731",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "extra_args = {}\n",
+    "model_type = models.torchvision.retinanet\n",
+    "backbone = model_type.backbones.resnet50_fpn\n",
+    "# Instantiate the model\n",
+    "model = model_type.model(backbone=backbone(pretrained=True), num_classes=len(parser.class_map), **extra_args) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "7b664cbf-3ab0-46df-a9d0-c4eb5c3c026d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Transforms\n",
+    "# size is set to 384 because EfficientDet requires its inputs to be divisible by 128\n",
+    "image_size = 384\n",
+    "train_tfms = tfms.A.Adapter([*tfms.A.aug_tfms(size=image_size, presize=512), tfms.A.Normalize()])\n",
+    "valid_tfms = tfms.A.Adapter([*tfms.A.resize_and_pad(image_size), tfms.A.Normalize()])\n",
+    "# Datasets\n",
+    "train_ds = Dataset(train_records, train_tfms)\n",
+    "valid_ds = Dataset(valid_records, valid_tfms)\n",
+    "# Data Loaders\n",
+    "train_dl = model_type.train_dl(train_ds, batch_size=8, num_workers=4, shuffle=True)\n",
+    "valid_dl = model_type.valid_dl(valid_ds, batch_size=8, num_workers=4, shuffle=False)\n",
+    "metrics = [COCOMetric(metric_type=COCOMetricType.bbox)]\n",
+    "learn = model_type.fastai.learner(dls=[train_dl, valid_dl], model=model, metrics=metrics)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "7bddb248-215d-4998-9d90-14ea6989c236",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/dnth/anaconda3/envs/icevision-gradio/lib/python3.8/site-packages/fastai/learner.py:56: UserWarning: Saved filed doesn't contain an optimizer state.\n",
+      "  elif with_opt: warn(\"Saved filed doesn't contain an optimizer state.\")\n"
+     ]
+    }
+   ],
+   "source": [
+    "learn = learn.load('model')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "745315f6-8aa5-486e-a7bc-e11348bec6a6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def show_preds(input_image, display_label, display_bbox, detection_threshold):\n",
+    "\n",
+    "    if detection_threshold==0: detection_threshold=0.5\n",
+    "\n",
+    "    img = PIL.Image.fromarray(input_image, 'RGB')\n",
+    "\n",
+    "    pred_dict  = model_type.end2end_detect(img, valid_tfms, model, class_map=class_map, detection_threshold=detection_threshold,\n",
+    "                                           display_label=display_label, display_bbox=display_bbox, return_img=True, \n",
+    "                                           font_size=16, label_color=\"#FF59D6\")\n",
+    "\n",
+    "    return pred_dict['img']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "63ac7fab-2068-4dbc-a464-0551b6fc12b2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7860/\n",
+      "Running on public URL: https://11839.gradio.app\n",
+      "\n",
+      "This share link will expire in 72 hours. To get longer links, send an email to: support@gradio.app\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/dnth/anaconda3/envs/icevision-gradio/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at  ../aten/src/ATen/native/TensorShape.cpp:2157.)\n",
+      "  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# display_chkbox = gr.inputs.CheckboxGroup([\"Label\", \"BBox\"], label=\"Display\", default=True)\n",
+    "display_chkbox_label = gr.inputs.Checkbox(label=\"Label\", default=True)\n",
+    "display_chkbox_box = gr.inputs.Checkbox(label=\"Box\", default=True)\n",
+    "\n",
+    "detection_threshold_slider = gr.inputs.Slider(minimum=0, maximum=1, step=0.1, default=0.5, label=\"Detection Threshold\")\n",
+    "\n",
+    "outputs = gr.outputs.Image(type=\"pil\")\n",
+    "\n",
+    "# Option 1: Get an image from local drive\n",
+    "gr_interface = gr.Interface(fn=show_preds, inputs=[\"image\", display_chkbox_label, display_chkbox_box,  detection_threshold_slider], outputs=outputs, title='IceApp - COCO')\n",
+    "\n",
+    "# #  Option 2: Grab an image from a webcam\n",
+    "# gr_interface = gr.Interface(fn=show_preds, inputs=[\"webcam\", display_chkbox_label, display_chkbox_box,  detection_threshold_slider], outputs=outputs, title='IceApp - COCO', live=False)\n",
+    "\n",
+    "# #  Option 3: Continuous image stream from the webcam\n",
+    "# gr_interface = gr.Interface(fn=show_preds, inputs=[\"webcam\", display_chkbox_label, display_chkbox_box,  detection_threshold_slider], outputs=outputs, title='IceApp - COCO', live=True)\n",
+    "\n",
+    "\n",
+    "gr_interface.launch(inline=False, share=True, debug=True)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "727a3589-364b-4bfd-9c32-bef5ebe34dbe",
+   "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": "3.8.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

requirements.txt

@@ -0,0 +1,9 @@
+#icevision[all]
+
+#opencv-python-headless
+
+git+https://github.com/dnth/icevision.git
+icedata
+
+#fastai
+#scikit-image