Upload 2 files

app.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[ ]:
+
+
+# importing required libraries
+from transformers import pipeline
+import gradio as gr
+from PIL import Image, ImageDraw
+
+# main function for object detection
+def detector(raw):
+    # Resize the image
+    WIDTH = 800
+    width, height = raw.size
+    ratio = float(WIDTH) / float(width)
+    new_h = height * ratio
+    ip_img = raw.resize((int(WIDTH), int(new_h)), Image.Resampling.LANCZOS)
+
+    # load the model pipeline and predict
+    outs = pipeline(model="hustvl/yolos-tiny")(ip_img)
+
+    # draw the image on the canvas
+    draw = ImageDraw.Draw(ip_img)
+
+    # draw the boxes with labels
+    for object in outs:
+        score = f"{object['score']*100:.2f}%"
+        label = object['label']
+        xmin, ymin, xmax, ymax = object['box'].values()
+        draw.rectangle((xmin, ymin, xmax, ymax), outline='red', width=1)
+        draw.text((xmin, ymin), f"{label}: {score}", fill="black")
+        
+    return ip_img
+
+demo = gr.Interface(fn=detector, 
+             inputs=gr.Image(type='pil'),
+             outputs=gr.Image(type='pil'), allow_flagging=False)
+demo.queue(True)
+demo.launch(debug=True, inline=False, show_api=False, share=False)
+

object_detection.ipynb

@@ -0,0 +1,109 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "0db6b22a-5180-45ad-bbcb-aeff29f1af15",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\faiza\\anaconda3\\envs\\hgace\\Lib\\site-packages\\gradio\\interface.py:331: UserWarning: The `allow_flagging` parameter in `Interface` nowtakes a string value ('auto', 'manual', or 'never'), not a boolean. Setting parameter to: 'never'.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7860\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Could not find image processor class in the image processor config or the model config. Loading based on pattern matching with the model's feature extractor configuration.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Keyboard interruption in main thread... closing server.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# importing required libraries\n",
+    "from transformers import pipeline\n",
+    "import gradio as gr\n",
+    "from PIL import Image, ImageDraw\n",
+    "\n",
+    "# main function for object detection\n",
+    "def detector(raw):\n",
+    "    # Resize the image\n",
+    "    WIDTH = 800\n",
+    "    width, height = raw.size\n",
+    "    ratio = float(WIDTH) / float(width)\n",
+    "    new_h = height * ratio\n",
+    "    ip_img = raw.resize((int(WIDTH), int(new_h)), Image.Resampling.LANCZOS)\n",
+    "\n",
+    "    # load the model pipeline and predict\n",
+    "    outs = pipeline(model=\"hustvl/yolos-tiny\")(ip_img)\n",
+    "\n",
+    "    # draw the image on the canvas\n",
+    "    draw = ImageDraw.Draw(ip_img)\n",
+    "\n",
+    "    # draw the boxes with labels\n",
+    "    for object in outs:\n",
+    "        score = f\"{object['score']*100:.2f}%\"\n",
+    "        label = object['label']\n",
+    "        xmin, ymin, xmax, ymax = object['box'].values()\n",
+    "        draw.rectangle((xmin, ymin, xmax, ymax), outline='red', width=1)\n",
+    "        draw.text((xmin, ymin), f\"{label}: {score}\", fill=\"black\")\n",
+    "        \n",
+    "    return ip_img\n",
+    "\n",
+    "demo = gr.Interface(fn=detector, \n",
+    "             inputs=gr.Image(type='pil'),\n",
+    "             outputs=gr.Image(type='pil'), allow_flagging=False)\n",
+    "demo.queue(True)\n",
+    "demo.launch(debug=True, inline=False, show_api=False, share=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}