demo-examples

analysis.ipynb

@@ -11,7 +11,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 1,
+      "execution_count": null,
       "metadata": {},
       "outputs": [],
       "source": [
@@ -245,7 +245,7 @@
         "                            'vectors'), \n",
         "                        indent=4),\n",
         "                    label_text_size=40,\n",
-        "                    label_rectangle_color='white',\n",
+        "                    label_fill_color='white',\n",
         "                ),\n",
         "            ]\n",
         "            for i\n",
@@ -278,6 +278,24 @@
         "print_matches(top_matches, 2, start=0)"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# len([i for i in top_matches if i['cosine_similarity_score'] < 1 and i['cosine_similarity_score'] > 0.99])\n",
+        "# len([i for i in top_matches if i['cosine_similarity_score'] >= 1])\n",
+        "# import random\n",
+        "# import shutil\n",
+        "# \n",
+        "# for matches in (top_matches[0:2] + random.sample([i for i in top_matches], 8)):\n",
+        "#     document_image_1 = matches['document_image_1']\n",
+        "#     document_image_2 = matches['document_image_2']\n",
+        "#     shutil.copyfile(f'./data/local-data/raw/RVL-CDIP-invoice/{document_image_1}', f'./demo-examples/{document_image_1}')\n",
+        "#     shutil.copyfile(f'./data/local-data/raw/RVL-CDIP-invoice/{document_image_2}', f'./demo-examples/{document_image_2}')"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -301,170 +319,18 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 22,
+      "execution_count": null,
       "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "Running on local URL:  http://127.0.0.1:7862\n",
-            "\n",
-            "To create a public link, set `share=True` in `launch()`.\n"
-          ]
-        },
-        {
-          "data": {
-            "text/html": [
-              "<div><iframe src=\"http://127.0.0.1:7862/\" 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"
-        },
-        {
-          "name": "stderr",
-          "output_type": "stream",
-          "text": [
-            "/Users/charleskabue/miniconda3/envs/dss-env/lib/python3.10/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /Users/runner/work/_temp/anaconda/conda-bld/pytorch_1695391816234/work/aten/src/ATen/native/TensorShape.cpp:3527.)\n",
-            "  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]\n"
-          ]
-        },
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "Keyboard interruption in main thread... closing server.\n"
-          ]
-        },
-        {
-          "data": {
-            "text/plain": []
-          },
-          "execution_count": 22,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
+      "outputs": [],
       "source": [
         "from main import app\n",
+        "import os\n",
         "\n",
         "model_path = '../detectron2-layout-parser/model_final.pth'\n",
         "config_path = '../detectron2-layout-parser/config.yaml'\n",
-        "examples = [\n",
-        "    '/Users/charleskabue/document-similarity-search/detectron2-layout-parser/example.1.jpg',\n",
-        "    '/Users/charleskabue/document-similarity-search/detectron2-layout-parser/example.2.jpg',\n",
-        "    '/Users/charleskabue/document-similarity-search/detectron2-layout-parser/example.3.jpg',\n",
-        "    ] * 5\n",
-        "app(model_path=model_path, config_path=config_path, examples=examples, debug=True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 16,
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "Running on local URL:  http://127.0.0.1:7861\n",
-            "\n",
-            "To create a public link, set `share=True` in `launch()`.\n"
-          ]
-        },
-        {
-          "data": {
-            "text/html": [
-              "<div><iframe src=\"http://127.0.0.1:7861/\" 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": 16,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "\n",
-        "import gradio as gr\n",
-        "\n",
-        "def classify_image(image):\n",
-        "  # Replace with your image classification logic\n",
-        "  # (e.g., using a pre-trained model or custom implementation)\n",
-        "  classification_results = {\"cat\": 0.8, \"dog\": 0.2}\n",
-        "  return classification_results\n",
-        "\n",
-        "image_input = gr.components.Image(type=\"pil\")  # Allow image upload\n",
-        "label = gr.components.Label(num_top_classes=3)  # Show top 3 predictions\n",
         "\n",
-        "interface = gr.Interface(classify_image, inputs=image_input, outputs=label)\n",
-        "interface.launch()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 15,
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "Running on local URL:  http://127.0.0.1:7861\n",
-            "\n",
-            "To create a public link, set `share=True` in `launch()`.\n"
-          ]
-        },
-        {
-          "data": {
-            "text/html": [
-              "<div><iframe src=\"http://127.0.0.1:7861/\" 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"
-        },
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "Keyboard interruption in main thread... closing server.\n"
-          ]
-        },
-        {
-          "data": {
-            "text/plain": []
-          },
-          "execution_count": 15,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "with gr.Blocks() as interface:\n",
-        "    document = gr.Image(\n",
-        "                type=\"pil\", label=f\"Document\", interactive=False, show_download_button=True)\n",
-        "    gr.Examples(\n",
-        "        examples=examples,\n",
-        "        inputs=document,\n",
-        "        label='Select any of these test document images')\n",
-        "interface.launch(debug=True)"
+        "examples = [f'./demo-examples/{filename}' for filename in os.listdir('./demo-examples/')]\n",
+        "app(model_path=model_path, config_path=config_path, examples=examples, debug=True)"
       ]
     }
   ],

app.py

@@ -14,4 +14,5 @@ from main import app
 
 model_path = './model/trained_model/model_final.pth'
 config_path = './model/trained_model/config.yaml'
-app(model_path=model_path, config_path=config_path, debug=True)
+examples = [f'./demo-examples/{filename}' for filename in os.listdir('./demo-examples/')]
+app(model_path=model_path, config_path=config_path, examples=examples, debug=True)