{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "25418b744a94403b87bdb1ee441b0f0f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_97604edfba2b406ba24c09444dd83669",
              "IPY_MODEL_bd19a87519164940b31566aa9dc83783",
              "IPY_MODEL_142b45c1a5b6428a8238c9f5a3b67af4"
            ],
            "layout": "IPY_MODEL_79d4c52b439b462e817c804c9ae5868a"
          }
        },
        "97604edfba2b406ba24c09444dd83669": {
          "model_module": "@jupyter-widgets/controls",
          "": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_8f2efd39a46c4652baf9c150961747e3",
            "placeholder": "​",
            "style": "IPY_MODEL_b5ab71c0700440abb2241e21c1ff2700",
            "value": "yolox_l0.05.onnx: 100%"
          }
        },
        "bd19a87519164940b31566aa9dc83783": {
          "model_module": "@jupyter-widgets/controls",
          "": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_2dc3b854904340da829f069019913c38",
            "max": 216625723,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_990c72a5cb1643da918286ec22a0549e",
            "value": 216625723
          }
        },
        "142b45c1a5b6428a8238c9f5a3b67af4": {
          "model_module": "@jupyter-widgets/controls",
          "": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_a9eca96f57de49eab0340ca23b760b27",
            "placeholder": "​",
            "style": "IPY_MODEL_32231abc0d4241dd94b1219c27e61158",
            "value": " 217M/217M [00:01<00:00, 152MB/s]"
          }
        },
        "79d4c52b439b462e817c804c9ae5868a": {
          "model_module": "@jupyter-widgets/base",
          "": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "8f2efd39a46c4652baf9c150961747e3": {
          "model_module": "@jupyter-widgets/base",
          "": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "b5ab71c0700440abb2241e21c1ff2700": {
          "model_module": "@jupyter-widgets/controls",
          "": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "2dc3b854904340da829f069019913c38": {
          "model_module": "@jupyter-widgets/base",
          "": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "990c72a5cb1643da918286ec22a0549e": {
          "model_module": "@jupyter-widgets/controls",
          "": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "a9eca96f57de49eab0340ca23b760b27": {
          "model_module": "@jupyter-widgets/base",
          "": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "32231abc0d4241dd94b1219c27e61158": {
          "model_module": "@jupyter-widgets/controls",
          "": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "20a9106670844c18b04aff1b71795212": {
          "model_module": "@jupyter-widgets/controls",
          "": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_670870037261419b93dd085c34eac92b",
              "IPY_MODEL_16858dfe37f14dafa82fc1eb35f41ccd",
              "IPY_MODEL_95d5d43f493d42149937016163ce4413"
            ],
            "layout": "IPY_MODEL_af27da8d0cf3455b9b316abbe0657ff9"
          }
        },
        "670870037261419b93dd085c34eac92b": {
          "model_module": "@jupyter-widgets/controls",
          "": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_a180017cc04445409c8f73b7bca5d7f3",
            "placeholder": "​",
            "style": "IPY_MODEL_9f7fe02ed6dc46feae3d0f5fb1c4989d",
            "value": "config.json: 100%"
          }
        },
        "16858dfe37f14dafa82fc1eb35f41ccd": {
          "model_module": "@jupyter-widgets/controls",
          "": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_98287e6ed278458eb18ed17a2fea408f",
            "max": 1469,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_2b77403b6c594536b50daa5ca7eb86e8",
            "value": 1469
          }
        },
        "95d5d43f493d42149937016163ce4413": {
          "model_module": "@jupyter-widgets/controls",
          "": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_217c6ca8a3134685904dd86fa59b20d9",
            "placeholder": "​",
            "style": "IPY_MODEL_fdf7d1d48cae4ab188dbc1535c857d8e",
            "value": " 1.47k/1.47k [00:00<00:00, 82.0kB/s]"
          }
        },
        "af27da8d0cf3455b9b316abbe0657ff9": {
          "model_module": "@jupyter-widgets/base",
          "": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "a180017cc04445409c8f73b7bca5d7f3": {
          "model_module": "@jupyter-widgets/base",
          "": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "9f7fe02ed6dc46feae3d0f5fb1c4989d": {
          "model_module": "@jupyter-widgets/controls",
          "": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "98287e6ed278458eb18ed17a2fea408f": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "2b77403b6c594536b50daa5ca7eb86e8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "217c6ca8a3134685904dd86fa59b20d9": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "fdf7d1d48cae4ab188dbc1535c857d8e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "d3f7dd522e6d40bf94e46a44e70ef614": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_13aa62f7ac34402ba6618bd63d6e2dd8",
              "IPY_MODEL_c81f1b0435d2462f9c9e672c11b01f5e",
              "IPY_MODEL_5feec57ac1b248d3bdd627ff139d8d52"
            ],
            "layout": "IPY_MODEL_391ed696c4824dc3ae25cb0add233071"
          }
        },
        "13aa62f7ac34402ba6618bd63d6e2dd8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_397bc80cd9844c5699abd62234539b5e",
            "placeholder": "​",
            "style": "IPY_MODEL_9b668233eb794d63ab9d168bd9e214b8",
            "value": "model.safetensors: 100%"
          }
        },
        "c81f1b0435d2462f9c9e672c11b01f5e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_c69ca675c5884f8593b45341fa898992",
            "max": 115434268,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_7813ca840b004910a36a5fd5ff3bbd78",
            "value": 115434268
          }
        },
        "5feec57ac1b248d3bdd627ff139d8d52": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_4ec1df63dd5743099a8dca4a8d677701",
            "placeholder": "​",
            "style": "IPY_MODEL_e75cfc4ba9ef49f081bda4bbea77f54a",
            "value": " 115M/115M [00:00<00:00, 196MB/s]"
          }
        },
        "391ed696c4824dc3ae25cb0add233071": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "397bc80cd9844c5699abd62234539b5e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "9b668233eb794d63ab9d168bd9e214b8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "c69ca675c5884f8593b45341fa898992": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "7813ca840b004910a36a5fd5ff3bbd78": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "4ec1df63dd5743099a8dca4a8d677701": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "e75cfc4ba9ef49f081bda4bbea77f54a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "d2a1416fa00e4e1bae2e9554f27a4ffc": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_9fee1d2a9ba04a9dac8094e3d73ba233",
              "IPY_MODEL_d5d2aac91f4f4d3598144d3ef0d9a5c1",
              "IPY_MODEL_cbe1eaebf48e44b8b12cc015351e4fa2"
            ],
            "layout": "IPY_MODEL_da5d88103dd7476588e8840e17b2c60c"
          }
        },
        "9fee1d2a9ba04a9dac8094e3d73ba233": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_47079e4440fb495bbc444fd84a38bd26",
            "placeholder": "​",
            "style": "IPY_MODEL_025ff4bbf0fd4fe98318e2b6572fa92e",
            "value": "model.safetensors: 100%"
          }
        },
        "d5d2aac91f4f4d3598144d3ef0d9a5c1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_f603dd0fa759420bb761014a8c16ffeb",
            "max": 46807446,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_88cde8b2165e4c6da739ad395c0fdbb2",
            "value": 46807446
          }
        },
        "cbe1eaebf48e44b8b12cc015351e4fa2": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_fbf0a24f3e7a4041808ee387e5bbb0c0",
            "placeholder": "​",
            "style": "IPY_MODEL_2e573c7670a34f638fc3b149bf761fa3",
            "value": " 46.8M/46.8M [00:00<00:00, 280MB/s]"
          }
        },
        "da5d88103dd7476588e8840e17b2c60c": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "47079e4440fb495bbc444fd84a38bd26": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "025ff4bbf0fd4fe98318e2b6572fa92e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "f603dd0fa759420bb761014a8c16ffeb": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "88cde8b2165e4c6da739ad395c0fdbb2": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "fbf0a24f3e7a4041808ee387e5bbb0c0": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "2e573c7670a34f638fc3b149bf761fa3": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# Unstructured - PDF to JSON and HTML"
      ],
      "metadata": {
        "id": "bXfuGoJFxrFx"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "- Author: [Pierre GUILLOU](https://www.linkedin.com/in/pierreguillou/)\n",
        "- Date: 18/12/2023 (previous version: 15/12/2023)\n",
        "- Blog post: [unstructured library | Get the JSON and HTML versions of any PDF (legal, financial, medical…), even PDF with tables!](https://medium.com/@pierre_guillou/unstructured-library-get-the-json-and-html-versions-of-any-pdf-legal-financial-medical-fb7738769caa)"
      ],
      "metadata": {
        "id": "JIGCcb8nW_W_"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Setup"
      ],
      "metadata": {
        "id": "Sp026Z98x1Lk"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "%%capture\n",
        "!apt-get install poppler-utils\n",
        "!apt-get install tesseract-ocr-all\n",
        "# unstructured 0.11.5\n",
        "# unstructured-inference 0.7.19\n",
        "!pip install unstructured[all-docs] unstructured-inference"
      ],
      "metadata": {
        "id": "xIfLbhqF70eP"
      },
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Restart session in Colab!**"
      ],
      "metadata": {
        "id": "7xJKVdcZxvgV"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Import libraries"
      ],
      "metadata": {
        "id": "BJIOzVJPKa3S"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "**You must have restarted your session before to run the next cell.**"
      ],
      "metadata": {
        "id": "L1AqgrNnKe6D"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import pathlib\n",
        "from pathlib import Path"
      ],
      "metadata": {
        "id": "hguT7OF9l5mp"
      },
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# select the partition function\n",
        "from unstructured.partition.pdf import partition_pdf # version unstructured 0.11.5"
      ],
      "metadata": {
        "id": "fPbNYGbbeTMK"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Define parameters for Unstructured's library\n",
        "\n",
        "## include_page_breaks\n",
        "# include page breaks (default is False)\n",
        "include_page_breaks = True\n",
        "\n",
        "## strategy\n",
        "# The strategy to use for partitioning the PDF. Valid strategies are \"hi_res\", \"ocr_only\", and \"fast\".\n",
        "# When using the \"hi_res\" strategy, the function uses a layout detection model to identify document elements.\n",
        "# hi_res\" is used for analyzing PDFs and extracting table structure (default is \"auto\")\n",
        "strategy = \"hi_res\"\n",
        "\n",
        "## infer_table_structure\n",
        "# Only applicable if `strategy=hi_res`.\n",
        "# If True, any Table elements that are extracted will also have a metadata field named \"text_as_html\" where the table's text content is rendered into an html string.\n",
        "# I.e., rows and cells are preserved.\n",
        "# Whether True or False, the \"text\" field is always present in any Table element and is the text content of the table (no structure).\n",
        "\n",
        "if strategy == \"hi_res\": infer_table_structure = True\n",
        "else: infer_table_structure = False\n",
        "\n",
        "## extract_element_types\n",
        "# Get images of tables\n",
        "if infer_table_structure == True: extract_element_types=['Table']\n",
        "else: extract_element_types=None\n",
        "\n",
        "## max_characters\n",
        "# The maximum number of characters to include in a partition (document element)\n",
        "# If None is passed, no maximum is applied.\n",
        "# Only applies to the \"ocr_only\" strategy (default is 1500)\n",
        "if strategy != \"ocr_only\": max_characters = None\n",
        "\n",
        "## languages\n",
        "# The languages to use for the Tesseract agent.\n",
        "# To use a language, you'll first need to install the appropriate Tesseract language pack.\n",
        "languages = [\"eng\"] # example if more than one \"eng+por\" (default is \"eng\")\n",
        "\n",
        "## model_name\n",
        "# @requires_dependencies(\"unstructured_inference\")\n",
        "# yolox: best model for table extraction. Other options are yolox_quantized, detectron2_onnx and chipper depending on file layout\n",
        "# source: https://unstructured-io.github.io/unstructured/best_practices/models.html\n",
        "hi_res_model_name = \"yolox\""
      ],
      "metadata": {
        "id": "J5sJ3QvilljH"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## PDF file"
      ],
      "metadata": {
        "id": "Z8_8oeTr-VFi"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "path = \"/content/\"\n",
        "filename = path + \"Quarterly.Financial.Report.Template.pdf\""
      ],
      "metadata": {
        "id": "5QLNHN7K-Wyf"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Get partition in json file"
      ],
      "metadata": {
        "id": "Wcjm6AtI-XxS"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Returns a List[Element] present in the pages of the parsed pdf document\n",
        "elements = partition_pdf(\n",
        "        filename=filename,\n",
        "        include_page_breaks=include_page_breaks,\n",
        "        strategy=strategy,\n",
        "        infer_table_structure=infer_table_structure,\n",
        "        extract_element_types=extract_element_types,\n",
        "        max_characters=max_characters,\n",
        "        languages=languages,\n",
        "        hi_res_model_name=hi_res_model_name,\n",
        "        )\n",
        "\n",
        "# get output as json\n",
        "from unstructured.staging.base import elements_to_json\n",
        "elements_to_json(elements, filename=f\"{filename}.json\") # Takes a while for file to show up on the Google Colab"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 308,
          "referenced_widgets": [
            "25418b744a94403b87bdb1ee441b0f0f",
            "97604edfba2b406ba24c09444dd83669",
            "bd19a87519164940b31566aa9dc83783",
            "142b45c1a5b6428a8238c9f5a3b67af4",
            "79d4c52b439b462e817c804c9ae5868a",
            "8f2efd39a46c4652baf9c150961747e3",
            "b5ab71c0700440abb2241e21c1ff2700",
            "2dc3b854904340da829f069019913c38",
            "990c72a5cb1643da918286ec22a0549e",
            "a9eca96f57de49eab0340ca23b760b27",
            "32231abc0d4241dd94b1219c27e61158",
            "20a9106670844c18b04aff1b71795212",
            "670870037261419b93dd085c34eac92b",
            "16858dfe37f14dafa82fc1eb35f41ccd",
            "95d5d43f493d42149937016163ce4413",
            "af27da8d0cf3455b9b316abbe0657ff9",
            "a180017cc04445409c8f73b7bca5d7f3",
            "9f7fe02ed6dc46feae3d0f5fb1c4989d",
            "98287e6ed278458eb18ed17a2fea408f",
            "2b77403b6c594536b50daa5ca7eb86e8",
            "217c6ca8a3134685904dd86fa59b20d9",
            "fdf7d1d48cae4ab188dbc1535c857d8e",
            "d3f7dd522e6d40bf94e46a44e70ef614",
            "13aa62f7ac34402ba6618bd63d6e2dd8",
            "c81f1b0435d2462f9c9e672c11b01f5e",
            "5feec57ac1b248d3bdd627ff139d8d52",
            "391ed696c4824dc3ae25cb0add233071",
            "397bc80cd9844c5699abd62234539b5e",
            "9b668233eb794d63ab9d168bd9e214b8",
            "c69ca675c5884f8593b45341fa898992",
            "7813ca840b004910a36a5fd5ff3bbd78",
            "4ec1df63dd5743099a8dca4a8d677701",
            "e75cfc4ba9ef49f081bda4bbea77f54a",
            "d2a1416fa00e4e1bae2e9554f27a4ffc",
            "9fee1d2a9ba04a9dac8094e3d73ba233",
            "d5d2aac91f4f4d3598144d3ef0d9a5c1",
            "cbe1eaebf48e44b8b12cc015351e4fa2",
            "da5d88103dd7476588e8840e17b2c60c",
            "47079e4440fb495bbc444fd84a38bd26",
            "025ff4bbf0fd4fe98318e2b6572fa92e",
            "f603dd0fa759420bb761014a8c16ffeb",
            "88cde8b2165e4c6da739ad395c0fdbb2",
            "fbf0a24f3e7a4041808ee387e5bbb0c0",
            "2e573c7670a34f638fc3b149bf761fa3"
          ]
        },
        "id": "SGNzEv6VQi-v",
        "outputId": "ede349a8-43e0-496e-fcce-7fea14aff12d"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "[nltk_data] Downloading package punkt to /root/nltk_data...\n",
            "[nltk_data]   Unzipping tokenizers/punkt.zip.\n",
            "[nltk_data] Downloading package averaged_perceptron_tagger to\n",
            "[nltk_data]     /root/nltk_data...\n",
            "[nltk_data]   Unzipping taggers/averaged_perceptron_tagger.zip.\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "yolox_l0.05.onnx:   0%|          | 0.00/217M [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "25418b744a94403b87bdb1ee441b0f0f"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "config.json:   0%|          | 0.00/1.47k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "20a9106670844c18b04aff1b71795212"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "model.safetensors:   0%|          | 0.00/115M [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "d3f7dd522e6d40bf94e46a44e70ef614"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "model.safetensors:   0%|          | 0.00/46.8M [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "d2a1416fa00e4e1bae2e9554f27a4ffc"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Some weights of the model checkpoint at microsoft/table-transformer-structure-recognition were not used when initializing TableTransformerForObjectDetection: ['model.backbone.conv_encoder.model.layer4.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer3.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer2.0.downsample.1.num_batches_tracked']\n",
            "- This IS expected if you are initializing TableTransformerForObjectDetection 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 TableTransformerForObjectDetection from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Get content in html file"
      ],
      "metadata": {
        "id": "AWgO5zxl--IP"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "def process_json_file(input_filename):\n",
        "    # Read the JSON file\n",
        "    with open(input_filename, 'r') as file:\n",
        "        data = json.load(file)\n",
        "\n",
        "    # Iterate over the JSON data and extract required table elements\n",
        "    extracted_elements = []\n",
        "    text_prev = \"\"\n",
        "    for i,entry in enumerate(data):\n",
        "        if entry[\"type\"] == \"Title\":\n",
        "            text = \"<h1>\" + entry[\"text\"] + \"</h1>\"\n",
        "        elif entry[\"type\"] == \"Table\":\n",
        "            text = entry[\"metadata\"][\"text_as_html\"]\n",
        "        else:\n",
        "            text = \"<p>\" + entry[\"text\"] + \"</p>\"\n",
        "\n",
        "        if text != text_prev: extracted_elements.append(text)\n",
        "        text_prev = text\n",
        "\n",
        "    # Write the extracted elements to the output file\n",
        "    html_start = \"\"\"\n",
        "    <!DOCTYPE html>\n",
        "    <html>\n",
        "    <head>\n",
        "    <title>Document Information</title>\n",
        "    <style>\n",
        "        table {\n",
        "            width: 100%;\n",
        "            border-collapse: collapse;\n",
        "        }\n",
        "        th, td {\n",
        "            border: 1px solid black;\n",
        "            padding: 8px;\n",
        "            text-align: left;\n",
        "        }\n",
        "        th {\n",
        "            background-color: #f2f2f2;\n",
        "        }\n",
        "    </style>\n",
        "    </head>\n",
        "    <body>\n",
        "    \"\"\"\n",
        "\n",
        "    html_end = \"\"\"\n",
        "    </body>\n",
        "    </html>\n",
        "    \"\"\"\n",
        "\n",
        "    output_file_html = path + Path(input_filename).name.replace(\".json\", \"\") + \"_\" + model_name + \".html\"\n",
        "    with open(output_file_html, 'w') as output_file:\n",
        "        output_file.write(html_start + \"\\n\")\n",
        "        for element in extracted_elements:\n",
        "            output_file.write(element + \"\\n\")\n",
        "        output_file.write(html_end + \"\\n\")\n",
        "\n",
        "    return str(output_file_html)"
      ],
      "metadata": {
        "id": "-mJdBB03m3ms"
      },
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import json\n",
        "output_file_html = process_json_file(f\"{filename}.json\") # It can take a while for the .html file to show up in Colab\n",
        "\n",
        "from google.colab import files\n",
        "files.download(output_file_html)"
      ],
      "metadata": {
        "id": "wES2N4yRnZk6",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 17
        },
        "outputId": "9d31cf8d-c3f7-408d-caad-447db28efe0b"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "download(\"download_6176995b-401f-4c18-b685-7831c65a16eb\", \"Quarterly.Financial.Report.Template.pdf_yolox.html\", 37559)"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# END"
      ],
      "metadata": {
        "id": "71l8DjsyAkyz"
      }
    }
  ]
}