{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "35d8939e-909d-45d8-bcf9-0ff1dccacfdf",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['bert.encoder.layer.6.output.LayerNorm.weight', 'bert.encoder.layer.6.attention.self.query.weight', 'bert.encoder.layer.3.attention.output.LayerNorm.bias', 'bert.encoder.layer.4.attention.self.value.bias', 'bert.encoder.layer.2.attention.self.value.bias', 'bert.encoder.layer.10.intermediate.dense.bias', 'bert.encoder.layer.3.intermediate.dense.bias', 'bert.encoder.layer.6.attention.self.value.weight', 'bert.encoder.layer.11.output.dense.bias', 'bert.encoder.layer.3.attention.self.value.bias', 'bert.encoder.layer.7.attention.self.value.bias', 'bert.encoder.layer.2.attention.output.dense.weight', 'bert.encoder.layer.11.attention.output.dense.weight', 'bert.encoder.layer.6.output.dense.bias', 'bert.encoder.layer.6.attention.output.dense.bias', 'bert.encoder.layer.4.output.LayerNorm.weight', 'bert.encoder.layer.9.output.dense.weight', 'bert.encoder.layer.9.attention.self.key.bias', 'bert.encoder.layer.3.attention.self.key.weight', 'bert.encoder.layer.3.intermediate.dense.weight', 'bert.encoder.layer.8.output.LayerNorm.weight', 'cls.seq_relationship.bias', 'bert.encoder.layer.6.attention.self.value.bias', 'bert.encoder.layer.10.output.LayerNorm.bias', 'bert.encoder.layer.10.attention.output.LayerNorm.bias', 'bert.encoder.layer.8.attention.self.key.bias', 'bert.encoder.layer.3.attention.self.query.weight', 'bert.encoder.layer.8.intermediate.dense.weight', 'bert.encoder.layer.8.attention.output.LayerNorm.bias', 'bert.encoder.layer.7.attention.output.dense.weight', 'bert.encoder.layer.9.attention.self.query.bias', 'bert.encoder.layer.2.output.dense.bias', 'bert.encoder.layer.6.attention.self.key.bias', 'bert.encoder.layer.4.attention.self.query.weight', 'bert.encoder.layer.2.attention.self.query.weight', 'bert.encoder.layer.11.attention.self.query.weight', 'bert.encoder.layer.3.attention.output.dense.weight', 'bert.encoder.layer.11.attention.output.LayerNorm.bias', 'bert.encoder.layer.10.attention.self.key.weight', 'bert.encoder.layer.3.attention.self.value.weight', 'bert.encoder.layer.5.attention.self.key.bias', 'bert.encoder.layer.5.intermediate.dense.bias', 'bert.encoder.layer.7.attention.self.key.weight', 'bert.encoder.layer.5.attention.self.value.weight', 'bert.encoder.layer.2.attention.output.dense.bias', 'bert.encoder.layer.2.output.dense.weight', 'bert.encoder.layer.6.attention.output.dense.weight', 'bert.encoder.layer.2.intermediate.dense.bias', 'bert.encoder.layer.9.attention.self.value.bias', 'bert.encoder.layer.6.intermediate.dense.bias', 'bert.encoder.layer.9.attention.output.dense.bias', 'bert.encoder.layer.7.attention.self.query.weight', 'bert.encoder.layer.8.attention.self.value.bias', 'bert.encoder.layer.4.attention.self.key.bias', 'bert.pooler.dense.bias', 'bert.encoder.layer.10.attention.output.dense.bias', 'bert.encoder.layer.5.output.LayerNorm.weight', 'cls.seq_relationship.weight', 'bert.encoder.layer.11.intermediate.dense.weight', 'bert.encoder.layer.2.attention.self.key.bias', 'bert.encoder.layer.10.attention.output.LayerNorm.weight', 'bert.encoder.layer.10.output.dense.bias', 'bert.encoder.layer.10.intermediate.dense.weight', 'bert.encoder.layer.4.intermediate.dense.weight', 'bert.encoder.layer.3.attention.self.key.bias', 'bert.encoder.layer.5.attention.self.query.weight', 'bert.encoder.layer.9.intermediate.dense.weight', 'bert.pooler.dense.weight', 'bert.encoder.layer.7.attention.output.LayerNorm.bias', 'bert.encoder.layer.11.output.LayerNorm.weight', 'bert.encoder.layer.5.attention.output.LayerNorm.bias', 'cls.predictions.transform.dense.weight', 'bert.encoder.layer.10.attention.self.value.bias', 'bert.encoder.layer.4.attention.self.query.bias', 'bert.encoder.layer.3.attention.self.query.bias', 'bert.encoder.layer.10.output.LayerNorm.weight', 'bert.encoder.layer.10.attention.self.key.bias', 'bert.encoder.layer.8.attention.self.value.weight', 'bert.encoder.layer.4.output.dense.bias', 'bert.encoder.layer.7.attention.self.key.bias', 'bert.encoder.layer.8.intermediate.dense.bias', 'bert.encoder.layer.7.intermediate.dense.weight', 'bert.encoder.layer.2.attention.self.key.weight', 'bert.encoder.layer.4.attention.output.dense.bias', 'bert.encoder.layer.6.output.dense.weight', 'bert.encoder.layer.8.attention.output.LayerNorm.weight', 'bert.encoder.layer.11.output.LayerNorm.bias', 'bert.encoder.layer.10.output.dense.weight', 'bert.encoder.layer.4.attention.output.LayerNorm.bias', 'bert.encoder.layer.11.output.dense.weight', 'bert.encoder.layer.8.output.dense.weight', 'bert.encoder.layer.5.attention.self.value.bias', 'bert.encoder.layer.4.intermediate.dense.bias', 'bert.encoder.layer.5.attention.self.key.weight', 'bert.encoder.layer.4.attention.self.key.weight', 'bert.encoder.layer.7.attention.self.query.bias', 'bert.encoder.layer.10.attention.self.query.weight', 'bert.encoder.layer.5.output.dense.bias', 'bert.encoder.layer.5.attention.output.dense.weight', 'bert.encoder.layer.7.output.dense.bias', 'bert.embeddings.token_type_embeddings.weight', 'bert.encoder.layer.8.output.dense.bias', 'bert.encoder.layer.7.attention.output.LayerNorm.weight', 'bert.encoder.layer.6.attention.self.key.weight', 'bert.encoder.layer.11.attention.output.LayerNorm.weight', 'bert.encoder.layer.7.output.LayerNorm.bias', 'bert.encoder.layer.9.attention.output.LayerNorm.weight', 'bert.encoder.layer.3.output.dense.bias', 'bert.encoder.layer.8.attention.self.query.bias', 'bert.encoder.layer.6.attention.self.query.bias', 'bert.encoder.layer.4.attention.output.dense.weight', 'bert.encoder.layer.6.intermediate.dense.weight', 'bert.encoder.layer.8.attention.output.dense.bias', 'bert.encoder.layer.10.attention.self.query.bias', 'bert.encoder.layer.8.attention.output.dense.weight', 'bert.encoder.layer.9.attention.output.dense.weight', 'bert.encoder.layer.5.output.dense.weight', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.weight', 'bert.encoder.layer.9.attention.self.query.weight', 'bert.encoder.layer.2.attention.output.LayerNorm.bias', 'bert.encoder.layer.4.attention.self.value.weight', 'bert.encoder.layer.6.output.LayerNorm.bias', 'bert.encoder.layer.10.attention.output.dense.weight', 'bert.encoder.layer.5.attention.self.query.bias', 'bert.encoder.layer.3.output.dense.weight', 'bert.encoder.layer.2.output.LayerNorm.weight', 'bert.encoder.layer.4.output.LayerNorm.bias', 'bert.encoder.layer.9.attention.self.value.weight', 'bert.encoder.layer.6.attention.output.LayerNorm.bias', 'bert.encoder.layer.11.attention.output.dense.bias', 'bert.encoder.layer.2.attention.output.LayerNorm.weight', 'bert.encoder.layer.7.output.LayerNorm.weight', 'bert.encoder.layer.2.output.LayerNorm.bias', 'bert.encoder.layer.3.output.LayerNorm.bias', 'cls.predictions.decoder.weight', 'bert.encoder.layer.5.attention.output.LayerNorm.weight', 'bert.encoder.layer.2.intermediate.dense.weight', 'bert.encoder.layer.11.attention.self.key.weight', 'bert.encoder.layer.11.attention.self.value.weight', 'bert.encoder.layer.9.intermediate.dense.bias', 'bert.encoder.layer.11.intermediate.dense.bias', 'bert.encoder.layer.11.attention.self.key.bias', 'bert.encoder.layer.2.attention.self.value.weight', 'bert.encoder.layer.3.output.LayerNorm.weight', 'bert.encoder.layer.9.output.LayerNorm.bias', 'bert.encoder.layer.5.intermediate.dense.weight', 'bert.encoder.layer.8.output.LayerNorm.bias', 'bert.encoder.layer.9.output.LayerNorm.weight', 'bert.encoder.layer.7.attention.self.value.weight', 'bert.encoder.layer.9.output.dense.bias', 'bert.encoder.layer.7.intermediate.dense.bias', 'bert.encoder.layer.6.attention.output.LayerNorm.weight', 'bert.encoder.layer.8.attention.self.query.weight', 'bert.encoder.layer.9.attention.self.key.weight', 'bert.encoder.layer.4.output.dense.weight', 'bert.encoder.layer.2.attention.self.query.bias', 'bert.encoder.layer.9.attention.output.LayerNorm.bias', 'bert.encoder.layer.3.attention.output.dense.bias', 'bert.encoder.layer.7.output.dense.weight', 'bert.encoder.layer.10.attention.self.value.weight', 'bert.encoder.layer.8.attention.self.key.weight', 'bert.encoder.layer.11.attention.self.value.bias', 'cls.predictions.transform.LayerNorm.bias', 'bert.encoder.layer.3.attention.output.LayerNorm.weight', 'bert.encoder.layer.5.attention.output.dense.bias', 'bert.encoder.layer.4.attention.output.LayerNorm.weight', 'bert.encoder.layer.11.attention.self.query.bias', 'cls.predictions.transform.dense.bias', 'bert.encoder.layer.7.attention.output.dense.bias', 'bert.encoder.layer.5.output.LayerNorm.bias']\n",
      "- This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
      "- This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
      "Some weights of BertModel were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['bert.encoder.layer.1.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.0.crossattention.self.query.bias', 'bert.encoder.layer.0.crossattention.output.dense.bias', 'bert.encoder.layer.1.crossattention.self.query.weight', 'bert.encoder.layer.0.crossattention.output.dense.weight', 'bert.encoder.layer.1.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.0.crossattention.self.key.weight', 'bert.encoder.layer.1.crossattention.output.dense.weight', 'bert.encoder.layer.0.crossattention.self.query.weight', 'bert.encoder.layer.0.crossattention.output.LayerNorm.bias', 'bert.encoder.layer.1.crossattention.self.key.weight', 'bert.encoder.layer.0.crossattention.self.key.bias', 'bert.encoder.layer.1.crossattention.output.dense.bias', 'bert.encoder.layer.0.crossattention.output.LayerNorm.weight', 'bert.encoder.layer.1.crossattention.self.value.weight', 'bert.encoder.layer.1.crossattention.self.value.bias', 'bert.encoder.layer.0.crossattention.self.value.bias', 'bert.encoder.layer.0.crossattention.self.value.weight', 'bert.encoder.layer.1.crossattention.self.query.bias', 'bert.encoder.layer.1.crossattention.self.key.bias']\n",
      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/encoder/layer/0/crossattention/self/query is tied\n",
      "/encoder/layer/0/crossattention/self/key is tied\n",
      "/encoder/layer/0/crossattention/self/value is tied\n",
      "/encoder/layer/0/crossattention/output/dense is tied\n",
      "/encoder/layer/0/crossattention/output/LayerNorm is tied\n",
      "/encoder/layer/0/intermediate/dense is tied\n",
      "/encoder/layer/0/output/dense is tied\n",
      "/encoder/layer/0/output/LayerNorm is tied\n",
      "/encoder/layer/1/crossattention/self/query is tied\n",
      "/encoder/layer/1/crossattention/self/key is tied\n",
      "/encoder/layer/1/crossattention/self/value is tied\n",
      "/encoder/layer/1/crossattention/output/dense is tied\n",
      "/encoder/layer/1/crossattention/output/LayerNorm is tied\n",
      "/encoder/layer/1/intermediate/dense is tied\n",
      "/encoder/layer/1/output/dense is tied\n",
      "/encoder/layer/1/output/LayerNorm is tied\n",
      "--------------\n",
      "/home/notebook/code/personal/S9049611/BLIP/output/blip_tagtotext_14m/blip_tagtotext_encoderdiv_tar_random_swin/caption_coco_finetune_tagparse_tagfinetune_threshold075_bceloss_tagsingle_5e6_epoch19_negative_1_05_pos_1_10/checkpoint_05.pth\n",
      "--------------\n",
      "load checkpoint from /home/notebook/code/personal/S9049611/BLIP/output/blip_tagtotext_14m/blip_tagtotext_encoderdiv_tar_random_swin/caption_coco_finetune_tagparse_tagfinetune_threshold075_bceloss_tagsingle_5e6_epoch19_negative_1_05_pos_1_10/checkpoint_05.pth\n",
      "vit: swin_b\n",
      "msg_v2 _IncompatibleKeys(missing_keys=['visual_encoder.layers.0.blocks.0.attn.relative_position_index', 'visual_encoder.layers.0.blocks.1.attn_mask', 'visual_encoder.layers.0.blocks.1.attn.relative_position_index', 'visual_encoder.layers.1.blocks.0.attn.relative_position_index', 'visual_encoder.layers.1.blocks.1.attn_mask', 'visual_encoder.layers.1.blocks.1.attn.relative_position_index', 'visual_encoder.layers.2.blocks.0.attn.relative_position_index', 'visual_encoder.layers.2.blocks.1.attn_mask', 'visual_encoder.layers.2.blocks.1.attn.relative_position_index', 'visual_encoder.layers.2.blocks.2.attn.relative_position_index', 'visual_encoder.layers.2.blocks.3.attn_mask', 'visual_encoder.layers.2.blocks.3.attn.relative_position_index', 'visual_encoder.layers.2.blocks.4.attn.relative_position_index', 'visual_encoder.layers.2.blocks.5.attn_mask', 'visual_encoder.layers.2.blocks.5.attn.relative_position_index', 'visual_encoder.layers.2.blocks.6.attn.relative_position_index', 'visual_encoder.layers.2.blocks.7.attn_mask', 'visual_encoder.layers.2.blocks.7.attn.relative_position_index', 'visual_encoder.layers.2.blocks.8.attn.relative_position_index', 'visual_encoder.layers.2.blocks.9.attn_mask', 'visual_encoder.layers.2.blocks.9.attn.relative_position_index', 'visual_encoder.layers.2.blocks.10.attn.relative_position_index', 'visual_encoder.layers.2.blocks.11.attn_mask', 'visual_encoder.layers.2.blocks.11.attn.relative_position_index', 'visual_encoder.layers.2.blocks.12.attn.relative_position_index', 'visual_encoder.layers.2.blocks.13.attn_mask', 'visual_encoder.layers.2.blocks.13.attn.relative_position_index', 'visual_encoder.layers.2.blocks.14.attn.relative_position_index', 'visual_encoder.layers.2.blocks.15.attn_mask', 'visual_encoder.layers.2.blocks.15.attn.relative_position_index', 'visual_encoder.layers.2.blocks.16.attn.relative_position_index', 'visual_encoder.layers.2.blocks.17.attn_mask', 'visual_encoder.layers.2.blocks.17.attn.relative_position_index', 'visual_encoder.layers.3.blocks.0.attn.relative_position_index', 'visual_encoder.layers.3.blocks.1.attn.relative_position_index'], unexpected_keys=[])\n"
     ]
    }
   ],
   "source": [
    "from PIL import Image\n",
    "import requests\n",
    "import torch\n",
    "from torchvision import transforms\n",
    "from torchvision.transforms.functional import InterpolationMode\n",
    "import ruamel_yaml as yaml\n",
    "from models.tag2text import tag2text_caption\n",
    "\n",
    "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
    "\n",
    "\n",
    "\n",
    "import gradio as gr\n",
    "\n",
    "image_size = 384\n",
    "\n",
    "\n",
    "normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],\n",
    "                                std=[0.229, 0.224, 0.225])\n",
    "transform = transforms.Compose([transforms.Resize((image_size, image_size)),transforms.ToTensor(),normalize])\n",
    "\n",
    "\n",
    "\n",
    "#######Swin Version\n",
    "pretrained = '/home/notebook/code/personal/S9049611/BLIP/output/blip_tagtotext_14m/blip_tagtotext_encoderdiv_tar_random_swin/caption_coco_finetune_tagparse_tagfinetune_threshold075_bceloss_tagsingle_5e6_epoch19_negative_1_05_pos_1_10/checkpoint_05.pth'\n",
    "\n",
    "config_file = 'configs/tag2text_caption.yaml'\n",
    "config = yaml.load(open(config_file, 'r'), Loader=yaml.Loader)\n",
    "\n",
    "\n",
    "model = tag2text_caption(pretrained=pretrained, image_size=image_size, vit=config['vit'], \n",
    "                    vit_grad_ckpt=config['vit_grad_ckpt'], vit_ckpt_layer=config['vit_ckpt_layer'],\n",
    "                    prompt=config['prompt'],config=config,threshold = 0.75 )\n",
    "\n",
    "model.eval()\n",
    "model = model.to(device)\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "9772dc6f-680d-45a7-b39c-23770eb5258e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7860\n",
      "Running on public URL: https://202e6e6a-b3d9-4c97.gradio.live\n",
      "\n",
      "This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"https://202e6e6a-b3d9-4c97.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'PIL.Image.Image'>\n",
      "<class 'PIL.Image.Image'>\n"
     ]
    }
   ],
   "source": [
    "\n",
    "def inference(raw_image, model_n, input_tag, strategy):\n",
    "    if model_n == 'Image Captioning':\n",
    "        raw_image = raw_image.resize((image_size, image_size))\n",
    "        print(type(raw_image))\n",
    "        image = transform(raw_image).unsqueeze(0).to(device)   \n",
    "        model.threshold = 0.75\n",
    "        if input_tag == '' or input_tag == 'none' or input_tag == 'None':\n",
    "            input_tag_list = None\n",
    "        else:\n",
    "            input_tag_list = []\n",
    "            input_tag_list.append(input_tag.replace(',',' | '))\n",
    "        # print(input_tag_list)\n",
    "        with torch.no_grad():\n",
    "            if strategy == \"Beam search\":\n",
    "                \n",
    "\n",
    "                caption, tag_predict = model.generate(image,tag_input = input_tag_list, return_tag_predict = True)\n",
    "                if input_tag_list == None:\n",
    "                    tag_1 = tag_predict\n",
    "                    tag_2 = ['none']\n",
    "                else:\n",
    "                    _, tag_1 = model.generate(image,tag_input = None, return_tag_predict = True)\n",
    "                    tag_2 = tag_predict\n",
    "\n",
    "            else:\n",
    "\n",
    "                caption,tag_predict = model.generate(image,  tag_input = input_tag_list,sample=True, top_p=0.9, max_length=20, min_length=5, return_tag_predict = True)\n",
    "                if input_tag_list == None:\n",
    "                    tag_1 = tag_predict\n",
    "                    tag_2 = ['none']\n",
    "                else:\n",
    "                    _, tag_1 = model.generate(image,tag_input = None, return_tag_predict = True)\n",
    "                    tag_2 = tag_predict\n",
    "            # return 'Caption: '+caption[0], 'Identified Tags:' + tag_predict[0]\n",
    "            # return tag_predict[0],caption[0]\n",
    "            return tag_1[0],tag_2[0],caption[0]\n",
    "            \n",
    "            # return 'caption: '+caption[0], tag_predict[0]\n",
    "\n",
    "    else:   \n",
    "        image_vq = transform_vq(raw_image).unsqueeze(0).to(device)  \n",
    "        with torch.no_grad():\n",
    "            answer = model_vq(image_vq, question, train=False, inference='generate') \n",
    "        return  'answer: '+answer[0]\n",
    "    \n",
    "inputs = [gr.inputs.Image(type='pil'),gr.inputs.Radio(choices=['Image Captioning'], type=\"value\", default=\"Image Captioning\", label=\"Task\"),gr.inputs.Textbox(lines=2, label=\"User Identified Tags (Optional, Enter with commas)\"),gr.inputs.Radio(choices=['Beam search','Nucleus sampling'], type=\"value\", default=\"Beam search\", label=\"Caption Decoding Strategy\")]\n",
    "\n",
    "# outputs = gr.outputs.Textbox(label=\"Output\")\n",
    "# outputs = [gr.outputs.Textbox(label=\"Image Caption\"),gr.outputs.Textbox(label=\"Identified Tags\")]\n",
    "outputs = [gr.outputs.Textbox(label=\"Model Identified Tags\"),gr.outputs.Textbox(label=\"User Identified Tags\"), gr.outputs.Textbox(label=\"Image Caption\") ]\n",
    "\n",
    "title = \"Tag2Text\"\n",
    "\n",
    "description = \"Gradio demo for Tag2Text: Guiding Language-Image Model via Image Tagging (Fudan University, OPPO Research Institute, International Digital Economy Academy).\"\n",
    "\n",
    "article = \"<p style='text-align: center'><a href='' target='_blank'>Tag2Text: Guiding Language-Image Model via Image Tagging</a> | <a href='' target='_blank'>Github Repo</a></p>\"\n",
    "\n",
    "demo = gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, examples=[['images/COCO_val2014_000000551338.jpg',\"Image Captioning\",\"none\",\"Beam search\"], \n",
    "                                                                                                                ['images/COCO_val2014_000000551338.jpg',\"Image Captioning\",\"fence, sky\",\"Beam search\"],\n",
    "                                                                                                                # ['images/COCO_val2014_000000551338.jpg',\"Image Captioning\",\"grass\",\"Beam search\"],\n",
    "                                                                                                                 ['images/COCO_val2014_000000483108.jpg',\"Image Captioning\",\"none\",\"Beam search\"],\n",
    "                                                                                                                 ['images/COCO_val2014_000000483108.jpg',\"Image Captioning\",\"electric cable\",\"Beam search\"],\n",
    "                                                                                                                  # ['images/COCO_val2014_000000483108.jpg',\"Image Captioning\",\"sky, train\",\"Beam search\"],\n",
    "                                                                                                                 ['images/COCO_val2014_000000483108.jpg',\"Image Captioning\",\"track, train\",\"Beam search\"] ,    \n",
    "                                                                                                                 ['images/COCO_val2014_000000483108.jpg',\"Image Captioning\",\"grass\",\"Beam search\"]     \n",
    "                                                                                                                ])\n",
    "\n",
    "\n",
    "demo.launch(share=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0da1f11b-e737-47a9-9b07-4e00c0835f63",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "73a4bb88-4200-4853-b1ba-34f0d4b6dc34",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3340a61f-c6bc-4ead-87ea-b26aa97b7a68",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d49e3de4-c3f7-4835-90eb-d0d013fc0ffb",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "205e0317-1701-4afd-8d67-bedb6959f350",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bf5301a5-80c5-4e44-835e-0160a97fef66",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f63d7a06-7625-4e1c-855d-177971217a0d",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c929e566-1a6e-4280-96eb-c434ef9a35d0",
   "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": "3.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}