first commit

app.py

@@ -0,0 +1,193 @@
+import gradio as gr
+import cv2
+import tempfile
+from ultralytics import YOLOv10
+import pandas as pd
+from gradio import processing_utils
+
+df = pd.read_csv('image_class.csv')
+df = df[['name', 'class']]
+df.drop_duplicates(inplace=True)
+print(len(df))
+df1 = pd.read_csv('image_class.csv')
+df1 = df1[['name', 'class', 'im_file']]
+df1['file_name'] = df1['im_file'].apply(lambda v: v.split('_')[-1].split('.')[0])
+df1.drop(columns='im_file', inplace=True)
+df1.drop_duplicates(inplace=True)
+print(df1)
+print(len(df1))
+
+def yolov10_inference(image, video, image_size, conf_threshold, iou_threshold):
+    model = YOLOv10('./drug_yolov10.pt')
+    # model = YOLOv10('./pills_yolov10.pt')
+    if image:
+        results = model.predict(source=image, imgsz=image_size, conf=conf_threshold, iou=iou_threshold)
+        annotated_image = results[0].plot()
+        # Print the detected objects' information (class, coordinates, and probability)
+        box = results[0].boxes
+        cls = [int(c) for c in box.cls.tolist()]
+        cnf = [round(f,2) for f in box.conf.tolist()]
+        clcf = '\n'.join([f'Class:{cls[i]} , Confidence:{cnf[i]*100}%' for i in range(len(cls))]) #list(zip(cls,cnf))
+        name = '\n'.join([df[df['class']==n]['name'].item() for n in cls])
+        file_name = image.split('_')[-1].split('.')[0]
+        print(f'file name: {file_name}')
+        try:
+            drug_name  = df1[df1['file_name']==file_name]['name'].item()
+            drug_class = df1[df1['file_name']==file_name]['class'].item()
+            drug_name = f'{drug_class}, {drug_name}'
+            print(drug_name)
+        except:
+            drug_name = 'No have data'
+        # print(cls)
+        # print(name)
+        # print(type(clcf))
+        # print("Object type:", box.cls)
+        # print("Coordinates:", box.xyxy)
+        # print("Probability:", box.conf)
+        # print('box.class data tyupe', type(box.cls.tolist()))
+        return annotated_image[:, :, ::-1], None, clcf, name, file_name, drug_name
+    else:
+        video_path = tempfile.mktemp(suffix=".webm")
+        with open(video_path, "wb") as f:
+            with open(video, "rb") as g:
+                f.write(g.read())
+
+        cap = cv2.VideoCapture(video_path)
+        fps = cap.get(cv2.CAP_PROP_FPS)
+        frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+        frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+
+        output_video_path = tempfile.mktemp(suffix=".webm")
+        out = cv2.VideoWriter(output_video_path, cv2.VideoWriter_fourcc(*'vp80'), fps, (frame_width, frame_height))
+
+        while cap.isOpened():
+            ret, frame = cap.read()
+            if not ret:
+                break
+
+            results = model.predict(source=frame, imgsz=image_size, conf=conf_threshold, iou=iou_threshold)
+            annotated_frame = results[0].plot()
+            out.write(annotated_frame)
+
+        cap.release()
+        out.release()
+
+        return None, output_video_path
+
+
+def yolov10_inference_for_examples(image, image_size, conf_threshold, iou_threshold):
+    annotated_image, _, output_class, output_name = yolov10_inference(image, None, image_size, conf_threshold, iou_threshold)
+    return annotated_image#, None, output_class, output_name
+
+def app():
+    with gr.Blocks():
+        with gr.Row():
+            with gr.Column():
+                # image = gr.Image(type="pil", label="Image", visible=True)
+                image = gr.Image(type="filepath", label="Image", visible=True)
+                video = gr.Video(label="Video", visible=False)
+                input_type = gr.Radio(
+                    choices=["Image", "Video"],
+                    value="Image",
+                    label="Input Type",
+                )
+                file_name = gr.Textbox(label='File Name')
+                file_name.change(outputs=file_name)
+                drug_name = gr.Textbox(label='Drug Name')
+                drug_name.change(outputs=drug_name)
+
+                image_size = gr.Slider(
+                    label="Image Size",
+                    minimum=0,
+                    maximum=1280,
+                    step=10,
+                    value=640,
+                )
+                conf_threshold = gr.Slider(
+                    label="Confidence Threshold",
+                    minimum=0.0,
+                    maximum=1.0,
+                    step=0.05,
+                    value=0.25,
+                )
+                iou_threshold = gr.Slider(
+                    label="IOU Threshold",
+                    minimum=0,
+                    maximum=1,
+                    step=0.1,
+                    value=0.6,
+                )
+                yolov10_infer = gr.Button(value="Detect Objects")
+            
+            with gr.Column():
+                output_image = gr.Image(type="numpy", label="Annotated Image", visible=True)
+                output_video = gr.Video(label="Annotated Video", visible=False)
+                output_name = gr.Textbox(label='Predicted Drug Name')
+                output_name.change(outputs=output_name)
+                output_class = gr.Textbox(label='Predicted Class')
+                output_class.change(outputs=output_class)
+
+        def update_visibility(input_type):
+            image = gr.update(visible=True) if input_type == "Image" else gr.update(visible=False)
+            video = gr.update(visible=False) if input_type == "Image" else gr.update(visible=True)
+            output_image = gr.update(visible=True) if input_type == "Image" else gr.update(visible=False)
+            output_video = gr.update(visible=False) if input_type == "Image" else gr.update(visible=True)
+            print(f'updated image: {image}')
+
+            return image, video, output_image, output_video
+
+        input_type.change(
+            fn=update_visibility,
+            inputs=[input_type],
+            outputs=[image, video, output_image, output_video],
+        )
+
+        def run_inference(image, video, image_size, conf_threshold, iou_threshold, input_type):
+            if input_type == "Image":
+                return yolov10_inference(image, None, image_size, conf_threshold, iou_threshold)
+            else:
+                return yolov10_inference(None, video, image_size, conf_threshold, iou_threshold)
+
+
+        yolov10_infer.click(
+            fn=run_inference,
+            inputs=[image, video, image_size, conf_threshold, iou_threshold, input_type],
+            outputs=[output_image, output_video, output_class, output_name, file_name, drug_name],
+        )
+
+        gr.Examples(
+            examples = [
+            ['./RXBASE-600_00071-1014-68_NLMIMAGE10_5715ABFD.jpg', 280, 0.2, 0.6],
+            ['./RXNAV-600_13668-0095-90_RXNAVIMAGE10_D145E8EF.jpg', 640, 0.2, 0.7],
+            ['./RXBASE-600_00074-7126-13_NLMIMAGE10_C003606B.jpg', 640, 0.2, 0.8],
+            ],
+            fn=yolov10_inference_for_examples,
+            inputs=[
+                image,
+                image_size,
+                conf_threshold,
+                iou_threshold,
+            ],
+            outputs=[output_image],
+            cache_examples='lazy',
+        )
+
+gradio_app = gr.Blocks()
+with gradio_app:
+    gr.HTML(
+        """
+    <h1 style='text-align: center'>
+    YOLOv10: Real-Time End-to-End Object Detection
+    </h1>
+    """)
+    gr.HTML(
+        """
+        <h3 style='text-align: center'>
+        <a href='https://arxiv.org/abs/2405.14458' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
+        </h3>
+        """)
+    with gr.Row():
+        with gr.Column():
+            app()
+if __name__ == '__main__':
+    gradio_app.launch()

drug_yolov10.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d953e3db8e56519197a3e6d74d2b078226f7f1cf1de07064631003acb4a493f3
+size 33211887

gradio_cached_examples/23/indices.csv

@@ -0,0 +1 @@
+0

gradio_cached_examples/23/log.csv

@@ -0,0 +1,2 @@
+Annotated Image,flag,username,timestamp
+"{""path"": ""gradio_cached_examples/23/Annotated Image/ba594e145eaf95ab5434/image.webp"", ""url"": ""/file=/tmp/gradio/1d7004412f6a7ce1df9e4d03b3144ae1bbc791ff/image.webp"", ""size"": null, ""orig_name"": ""image.webp"", ""mime_type"": null, ""is_stream"": false, ""meta"": {""_type"": ""gradio.FileData""}}",,,2024-06-07 17:57:56.712008

gradio_cached_examples/24/indices.csv

@@ -0,0 +1 @@
+0

gradio_cached_examples/24/log.csv

@@ -0,0 +1,2 @@
+Annotated Image,flag,username,timestamp
+"{""path"": ""gradio_cached_examples/24/Annotated Image/218b53a36785220fa9c1/image.webp"", ""url"": ""/file=/tmp/gradio/1d7004412f6a7ce1df9e4d03b3144ae1bbc791ff/image.webp"", ""size"": null, ""orig_name"": ""image.webp"", ""mime_type"": null, ""is_stream"": false, ""meta"": {""_type"": ""gradio.FileData""}}",,,2024-06-07 21:20:45.740938

requirements.txt

@@ -0,0 +1,4 @@
+gradio==4.32.1
+opencv_python==4.8.1.78
+opencv_python_headless==4.8.0.74
+git+https://github.com/THU-MIG/yolov10

test.ipynb

@@ -0,0 +1,194 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2111\n",
+      "                                            name  class     file_name\n",
+      "0     Loperamide Hydrochloride 2 MG Oral Capsule   1052  26211358.jpg\n",
+      "1                 Minocycline 50 MG Oral Capsule   1137  36231B28.jpg\n",
+      "2               Nortriptyline 10 MG Oral Capsule   1193  24231228.jpg\n",
+      "3               Nortriptyline 25 MG Oral Capsule   1194  20231018.jpg\n",
+      "4               Nortriptyline 50 MG Oral Capsule   1195  2D2316D8.jpg\n",
+      "...                                          ...    ...           ...\n",
+      "4327        Enalapril Maleate 2.5 MG Oral Tablet    708  DC4D6E2B.jpg\n",
+      "4328                  quinapril 5 MG Oral Tablet   1844  EA507553.jpg\n",
+      "4329         trospium chloride 20 MG Oral Tablet   1959  3C519E2C.jpg\n",
+      "4330               metaxalone 400 MG Oral Tablet   1749  C6506353.jpg\n",
+      "4331              naratriptan 2.5 MG Oral Tablet   1775  66453369.jpg\n",
+      "\n",
+      "[4332 rows x 3 columns]\n",
+      "4332\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('image_class.csv')\n",
+    "df = df[['name', 'class']]\n",
+    "df.drop_duplicates(inplace=True)\n",
+    "print(len(df))\n",
+    "df1 = pd.read_csv('image_class.csv')\n",
+    "df1 = df1[['name', 'class', 'im_file']]\n",
+    "df1['file_name'] = df1['im_file'].apply(lambda v: v.split('_')[-1])\n",
+    "df1.drop(columns='im_file', inplace=True)\n",
+    "df1.drop_duplicates(inplace=True)\n",
+    "print(df1)\n",
+    "print(len(df1))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>name</th>\n",
+       "      <th>class</th>\n",
+       "      <th>file_name</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>213</th>\n",
+       "      <td>pregabalin 75 MG Oral Capsule [Lyrica]</td>\n",
+       "      <td>1831</td>\n",
+       "      <td>5715ABFD.jpg</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                       name  class     file_name\n",
+       "213  pregabalin 75 MG Oral Capsule [Lyrica]   1831  5715ABFD.jpg"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# df1[df1.file_name.str.endswith('26211358.jpg')]\n",
+    "df1[df1.file_name.str.endswith('5715ABFD.jpg')]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "TypeError",
+     "evalue": "'StringMethods' object is not callable",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[8], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;66;03m# file_name = '00071-1014-68_NLMIMAGE10_5715ABFD.jpeg'\u001b[39;00m\n\u001b[1;32m      2\u001b[0m file_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m23155-0055-19_NLMIMAGE10_66453369.jpg\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m----> 3\u001b[0m df1[\u001b[43mdf1\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mfile_name\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstr\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m_\u001b[39m\u001b[38;5;124m'\u001b[39m,\u001b[38;5;241m1\u001b[39m)[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\u001b[38;5;241m==\u001b[39mfile_name]\n",
+      "\u001b[0;31mTypeError\u001b[0m: 'StringMethods' object is not callable"
+     ]
+    }
+   ],
+   "source": [
+    "# file_name = '00071-1014-68_NLMIMAGE10_5715ABFD.jpeg'\n",
+    "file_name = '23155-0055-19_NLMIMAGE10_66453369.jpg'\n",
+    "df1[df1['file_name'].str().split('_',1)[-1]==file_name]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0       [00093-0311-01, RXNAVIMAGE10, 26211358.jpg]\n",
+       "1       [00093-3165-01, RXNAVIMAGE10, 36231B28.jpg]\n",
+       "2       [00093-0810-01, RXNAVIMAGE10, 24231228.jpg]\n",
+       "3       [00093-0811-01, RXNAVIMAGE10, 20231018.jpg]\n",
+       "4       [00093-0812-01, RXNAVIMAGE10, 2D2316D8.jpg]\n",
+       "                           ...                     \n",
+       "8629      [16714-0442-01, NLMIMAGE10, DC4D6E2B.jpg]\n",
+       "8630      [31722-0267-90, NLMIMAGE10, EA507553.jpg]\n",
+       "8631      [00574-0145-60, NLMIMAGE10, 3C519E2C.jpg]\n",
+       "8632      [64720-0126-10, NLMIMAGE10, C6506353.jpg]\n",
+       "8633      [23155-0055-19, NLMIMAGE10, 66453369.jpg]\n",
+       "Name: file_name, Length: 8634, dtype: object"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1.file_name.str.split('_')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "yolov9",
+   "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": "3.9.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}