{
"cells": [
{
"cell_type": "code",
"execution_count": 5,
"id": "f51609a4",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"& was unexpected at this time.\n"
]
}
],
"source": [
"!pip install gradio"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "9d989bf2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2.16.1\n"
]
}
],
"source": [
"import tensorflow as tf\n",
"print(tf.version.VERSION)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "d789a404",
"metadata": {},
"outputs": [],
"source": [
"from tensorflow.keras.models import load_model\n",
"from tensorflow.keras.layers import TFSMLayer"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "1ca99ffa",
"metadata": {},
"outputs": [
{
"ename": "OSError",
"evalue": "SavedModel file does not exist at: mask_detector.model\\{saved_model.pbtxt|saved_model.pb}",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mOSError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[7], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mTFSMLayer\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmask_detector.model\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcall_endpoint\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mserving_default\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n",
"File \u001b[1;32md:\\Programming\\Projects\\Mask_detector\\maskVenv\\Lib\\site-packages\\keras\\src\\export\\export_lib.py:710\u001b[0m, in \u001b[0;36mTFSMLayer.__init__\u001b[1;34m(self, filepath, call_endpoint, call_training_endpoint, trainable, name, dtype)\u001b[0m\n\u001b[0;32m 707\u001b[0m \u001b[38;5;66;03m# Initialize an empty layer, then add_weight() etc. as needed.\u001b[39;00m\n\u001b[0;32m 708\u001b[0m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__init__\u001b[39m(trainable\u001b[38;5;241m=\u001b[39mtrainable, name\u001b[38;5;241m=\u001b[39mname, dtype\u001b[38;5;241m=\u001b[39mdtype)\n\u001b[1;32m--> 710\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_reloaded_obj \u001b[38;5;241m=\u001b[39m \u001b[43mtf\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msaved_model\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 712\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfilepath \u001b[38;5;241m=\u001b[39m filepath\n\u001b[0;32m 713\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcall_endpoint \u001b[38;5;241m=\u001b[39m call_endpoint\n",
"File \u001b[1;32md:\\Programming\\Projects\\Mask_detector\\maskVenv\\Lib\\site-packages\\tensorflow\\python\\saved_model\\load.py:912\u001b[0m, in \u001b[0;36mload\u001b[1;34m(export_dir, tags, options)\u001b[0m\n\u001b[0;32m 910\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(export_dir, os\u001b[38;5;241m.\u001b[39mPathLike):\n\u001b[0;32m 911\u001b[0m export_dir \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39mfspath(export_dir)\n\u001b[1;32m--> 912\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[43mload_partial\u001b[49m\u001b[43m(\u001b[49m\u001b[43mexport_dir\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtags\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mroot\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[0;32m 913\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m result\n",
"File \u001b[1;32md:\\Programming\\Projects\\Mask_detector\\maskVenv\\Lib\\site-packages\\tensorflow\\python\\saved_model\\load.py:1016\u001b[0m, in \u001b[0;36mload_partial\u001b[1;34m(export_dir, filters, tags, options)\u001b[0m\n\u001b[0;32m 1011\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m tags \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(tags, \u001b[38;5;28mset\u001b[39m):\n\u001b[0;32m 1012\u001b[0m \u001b[38;5;66;03m# Supports e.g. tags=SERVING and tags=[SERVING]. Sets aren't considered\u001b[39;00m\n\u001b[0;32m 1013\u001b[0m \u001b[38;5;66;03m# sequences for nest.flatten, so we put those through as-is.\u001b[39;00m\n\u001b[0;32m 1014\u001b[0m tags \u001b[38;5;241m=\u001b[39m nest\u001b[38;5;241m.\u001b[39mflatten(tags)\n\u001b[0;32m 1015\u001b[0m saved_model_proto, debug_info \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m-> 1016\u001b[0m \u001b[43mloader_impl\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse_saved_model_with_debug_info\u001b[49m\u001b[43m(\u001b[49m\u001b[43mexport_dir\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[0;32m 1018\u001b[0m loader \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m 1019\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\u001b[38;5;28mlen\u001b[39m(saved_model_proto\u001b[38;5;241m.\u001b[39mmeta_graphs) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m1\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m\n\u001b[0;32m 1020\u001b[0m saved_model_proto\u001b[38;5;241m.\u001b[39mmeta_graphs[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mHasField(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mobject_graph_def\u001b[39m\u001b[38;5;124m\"\u001b[39m)):\n",
"File \u001b[1;32md:\\Programming\\Projects\\Mask_detector\\maskVenv\\Lib\\site-packages\\tensorflow\\python\\saved_model\\loader_impl.py:59\u001b[0m, in \u001b[0;36mparse_saved_model_with_debug_info\u001b[1;34m(export_dir)\u001b[0m\n\u001b[0;32m 46\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mparse_saved_model_with_debug_info\u001b[39m(export_dir):\n\u001b[0;32m 47\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Reads the savedmodel as well as the graph debug info.\u001b[39;00m\n\u001b[0;32m 48\u001b[0m \n\u001b[0;32m 49\u001b[0m \u001b[38;5;124;03m Args:\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 57\u001b[0m \u001b[38;5;124;03m parsed. Missing graph debug info file is fine.\u001b[39;00m\n\u001b[0;32m 58\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[1;32m---> 59\u001b[0m saved_model \u001b[38;5;241m=\u001b[39m \u001b[43mparse_saved_model\u001b[49m\u001b[43m(\u001b[49m\u001b[43mexport_dir\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 61\u001b[0m debug_info_path \u001b[38;5;241m=\u001b[39m file_io\u001b[38;5;241m.\u001b[39mjoin(\n\u001b[0;32m 62\u001b[0m path_helpers\u001b[38;5;241m.\u001b[39mget_debug_dir(export_dir),\n\u001b[0;32m 63\u001b[0m constants\u001b[38;5;241m.\u001b[39mDEBUG_INFO_FILENAME_PB)\n\u001b[0;32m 64\u001b[0m debug_info \u001b[38;5;241m=\u001b[39m graph_debug_info_pb2\u001b[38;5;241m.\u001b[39mGraphDebugInfo()\n",
"File \u001b[1;32md:\\Programming\\Projects\\Mask_detector\\maskVenv\\Lib\\site-packages\\tensorflow\\python\\saved_model\\loader_impl.py:119\u001b[0m, in \u001b[0;36mparse_saved_model\u001b[1;34m(export_dir)\u001b[0m\n\u001b[0;32m 117\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mIOError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCannot parse file \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpath_to_pbtxt\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mstr\u001b[39m(e)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[0;32m 118\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 119\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mIOError\u001b[39;00m(\n\u001b[0;32m 120\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mSavedModel file does not exist at: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mexport_dir\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00mos\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39msep\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 121\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m{{\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00mconstants\u001b[38;5;241m.\u001b[39mSAVED_MODEL_FILENAME_PBTXT\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m|\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 122\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mconstants\u001b[38;5;241m.\u001b[39mSAVED_MODEL_FILENAME_PB\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m}}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 123\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m saved_model\n",
"\u001b[1;31mOSError\u001b[0m: SavedModel file does not exist at: mask_detector.model\\{saved_model.pbtxt|saved_model.pb}"
]
}
],
"source": [
"model = TFSMLayer(\"mask_detector.model\", call_endpoint='serving_default')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "c3735b5c",
"metadata": {},
"outputs": [
{
"ename": "ValueError",
"evalue": "File format not supported: filepath=mask_detector.model. Keras 3 only supports V3 `.keras` files and legacy H5 format files (`.h5` extension). Note that the legacy SavedModel format is not supported by `load_model()` in Keras 3. In order to reload a TensorFlow SavedModel as an inference-only layer in Keras 3, use `keras.layers.TFSMLayer(mask_detector.model, call_endpoint='serving_default')` (note that your `call_endpoint` might have a different name).",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[3], line 2\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[38;5;66;03m# load the face mask detector model from disk\u001b[39;00m\n\u001b[1;32m----> 2\u001b[0m maskNet \u001b[38;5;241m=\u001b[39m \u001b[43mload_model\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmask_detector.model\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
"File \u001b[1;32md:\\Programming\\Projects\\Mask_detector\\maskVenv\\Lib\\site-packages\\keras\\src\\saving\\saving_api.py:193\u001b[0m, in \u001b[0;36mload_model\u001b[1;34m(filepath, custom_objects, compile, safe_mode)\u001b[0m\n\u001b[0;32m 187\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m 188\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFile not found: filepath=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfilepath\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 189\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPlease ensure the file is an accessible `.keras` \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 190\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mzip file.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 191\u001b[0m )\n\u001b[0;32m 192\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 193\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m 194\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFile format not supported: filepath=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfilepath\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 195\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mKeras 3 only supports V3 `.keras` files and \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 196\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlegacy H5 format files (`.h5` extension). \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 197\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNote that the legacy SavedModel format is not \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 198\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msupported by `load_model()` in Keras 3. In \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 199\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124morder to reload a TensorFlow SavedModel as an \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 200\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124minference-only layer in Keras 3, use \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 201\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`keras.layers.TFSMLayer(\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 202\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfilepath\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m, call_endpoint=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mserving_default\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m)` \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 203\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m(note that your `call_endpoint` \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 204\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmight have a different name).\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 205\u001b[0m )\n",
"\u001b[1;31mValueError\u001b[0m: File format not supported: filepath=mask_detector.model. Keras 3 only supports V3 `.keras` files and legacy H5 format files (`.h5` extension). Note that the legacy SavedModel format is not supported by `load_model()` in Keras 3. In order to reload a TensorFlow SavedModel as an inference-only layer in Keras 3, use `keras.layers.TFSMLayer(mask_detector.model, call_endpoint='serving_default')` (note that your `call_endpoint` might have a different name)."
]
}
],
"source": [
"# load the face mask detector model from disk\n",
"maskNet = load_model(\"mask_detector.model\")"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "7a0dea2a",
"metadata": {},
"outputs": [],
"source": [
"# import the necessary packages\n",
"from tensorflow.keras.applications.mobilenet_v2 import preprocess_input\n",
"from tensorflow.keras.preprocessing.image import img_to_array\n",
"from tensorflow.keras.models import load_model\n",
"from imutils.video import VideoStream\n",
"import numpy as np\n",
"import imutils\n",
"import time\n",
"import cv2\n",
"import os"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "3ea65ae1",
"metadata": {},
"outputs": [],
"source": [
"import gradio as gr"
]
},
{
"cell_type": "code",
"execution_count": 77,
"id": "616836d6",
"metadata": {},
"outputs": [],
"source": [
"def detect_and_predict_mask(frame, faceNet, maskNet):\n",
" try:\n",
" # grab the dimensions of the frame and then construct a blob from it\n",
" (h, w) = frame.shape[:2]\n",
" blob = cv2.dnn.blobFromImage(frame, 1.0, (224,224),(104.0,177.0,123.0) )\n",
"\n",
" # pass the blob through the network and obtain the face detections\n",
" faceNet.setInput(blob)\n",
" detections = faceNet.forward()\n",
" print(detections.shape)\n",
"\n",
" # initialize our list of faces, their corresponding locations, and the list of predictions from our face mask network\n",
" faces = []\n",
" locs = []\n",
" preds = []\n",
" # loop over the detections\n",
" for i in range(0,detections.shape[2]):\n",
" # extract the confidence (i.e., probability) associated with the detection\n",
" confidence = detections[0,0,i,2]\n",
"\n",
" # filter out weak detections by ensuring the confidence is greater than minimum confidence\n",
" if confidence > 0.5:\n",
" # compute the (x, y)-cordinates of the bounding box for the object\n",
" box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])\n",
" (startX, startY, endX, endY) = box.astype(\"int\")\n",
"\n",
" # ensure the bounding boxes fall within the dimensions of the frame\n",
" (startX , startY) = (max(0,startX) , max(0,startY))\n",
" (endX, endY) = (min(w-1,endX) , min(h-1,endY))\n",
"\n",
" # extract the face ROI, convert it from BGR to RGB channel ordering, resize it to 224x224, and preprocess it face=frame[startY:endY, startX:endX]\n",
" # bounding mask only for face detected\n",
" face = frame[startY:endY , startX:endX]\n",
" face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)\n",
" face = cv2.resize(face, (224,224))\n",
" face = img_to_array(face)\n",
" face = preprocess_input(face)\n",
"\n",
" # add the face and bounding boxes to their respective lists\n",
" faces.append(face)\n",
" locs.append((startX, startY, endX, endY))\n",
"\n",
" # only make a predictions if at least one face was detected\n",
" if len(faces) > 0:\n",
" # far faster inference we'll make batch predictions on *all* faces at the same time rather than one-by-one predictions in the above 'for' loop\n",
" faces = np.array(faces,dtype=\"float32\")\n",
" preds = maskNet.predict(faces, batch_size=32)\n",
"\n",
" # return a 2-tuple of the face locations and their corresponding locations\n",
" return (locs, preds)\n",
" except Exception as e:\n",
" print(e)"
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "da40c96f",
"metadata": {},
"outputs": [],
"source": [
"# load our serialized face detector model from disk\n",
"prototxtPath = r\"deploy.prototxt.txt\"\n",
"weightsPath = r\"res10_300x300_ssd_iter_140000.caffemodel\"\n",
"faceNet = cv2.dnn.readNet(prototxtPath,weightsPath)\n",
"\n",
"# load the face mask detector model from disk\n",
"maskNet = load_model(\"mask_detector.model\")"
]
},
{
"cell_type": "code",
"execution_count": 106,
"id": "b5751c2c",
"metadata": {},
"outputs": [],
"source": [
"import numpy"
]
},
{
"cell_type": "code",
"execution_count": 134,
"id": "04f7d873",
"metadata": {},
"outputs": [],
"source": [
"def webcam_stream(frame):\n",
" if type(frame)==type(None):\n",
" return\n",
" while True:\n",
" try:\n",
" # grab the frame from the threaded video stream and resize it to have a max width of 400 pixels\n",
" frame = imutils.resize(frame,width=400)\n",
"\n",
" # detect faces in the frame and determine if they are wearing a face mask or not\n",
" (locs, preds) = detect_and_predict_mask(frame, faceNet, maskNet)\n",
"\n",
" # loop over the detected face locations and their correspondings locations\n",
" for (box, pred) in zip(locs, preds):\n",
" # unpack the bounding box and predictions\n",
" (startX, startY, endX, endY) = box\n",
" (mask, withoutMask) = pred\n",
"\n",
" # determine the class label and color we'll use to draw the bounding box and text\n",
" label = \"Mask\" if mask> withoutMask else \"No Mask\"\n",
" color = (0,255,0) if label==\"Mask\" else (0,0,255)\n",
"\n",
" # include the probability in the label\n",
" label = \"{}: {:.2f}%\".format(label,max(mask, withoutMask) *100)\n",
"\n",
" # display the label and bounding box rectangle on the output frame\n",
" cv2.putText(frame,label,(startX,startY-10), cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)\n",
" cv2.rectangle(frame, (startX,startY), (endX,endY),color,2)\n",
" \n",
"\n",
" # show the output frame\n",
" cv2.imshow(\"Frame\",frame)\n",
" key = cv2.waitKey(1) & 0xFF\n",
"\n",
" # if the 'q' key was pressed, break from the loop\n",
" if key == ord(\"q\"):\n",
" break\n",
" except Exception as e:\n",
" print(e)\n",
" \n",
" return frame\n",
"# do a bit of cleanup\n",
"# cv2.destroyAllWindows()"
]
},
{
"cell_type": "code",
"execution_count": 132,
"id": "5c845891",
"metadata": {},
"outputs": [],
"source": [
"# def webcam_stream(vid):\n",
"# return vid"
]
},
{
"cell_type": "code",
"execution_count": 133,
"id": "b30a1bf8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running on local URL: http://127.0.0.1:7892\n",
"\n",
"To create a public link, set `share=True` in `launch()`.\n"
]
},
{
"data": {
"text/html": [
""
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": []
},
"execution_count": 133,
"metadata": {},
"output_type": "execute_result"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"(1, 1, 200, 7)\n",
"1/1 [==============================] - 0s 64ms/step\n",
"\n",
"\n",
"(1, 1, 200, 7)\n",
"1/1 [==============================] - 0s 67ms/step\n",
"\n"
]
}
],
"source": [
"webcam = gr.Image(source=\"webcam\",every=\"float\",mirror_webcam=True)\n",
"output = gr.Image(source=\"webcam\")\n",
"# Create a Gradio interface with the webcam_stream function\n",
"app = gr.Interface(webcam_stream,inputs=webcam,outputs=output,live=True)\n",
"\n",
"# Start the app\n",
"app.launch() "
]
},
{
"cell_type": "code",
"execution_count": 139,
"id": "d6124d93",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Closing server running on port: 7871\n",
"Closing server running on port: 7882\n",
"Closing server running on port: 7887\n",
"Closing server running on port: 7867\n",
"Closing server running on port: 7868\n",
"Closing server running on port: 7866\n",
"Closing server running on port: 7879\n",
"Closing server running on port: 7865\n",
"Closing server running on port: 7860\n",
"Closing server running on port: 7876\n",
"Closing server running on port: 7868\n",
"Closing server running on port: 7863\n",
"Closing server running on port: 7867\n",
"Closing server running on port: 7860\n",
"Closing server running on port: 7873\n",
"Closing server running on port: 7886\n",
"Closing server running on port: 7888\n",
"Closing server running on port: 7872\n",
"Closing server running on port: 7870\n",
"Closing server running on port: 7870\n",
"Closing server running on port: 7869\n",
"Closing server running on port: 7882\n",
"Closing server running on port: 7863\n",
"Closing server running on port: 7892\n",
"Closing server running on port: 7890\n",
"Closing server running on port: 7875\n",
"Closing server running on port: 7889\n",
"Closing server running on port: 7869\n",
"Closing server running on port: 7878\n",
"Closing server running on port: 7885\n",
"Closing server running on port: 7877\n",
"Closing server running on port: 7884\n",
"Closing server running on port: 7891\n",
"Closing server running on port: 7880\n",
"Closing server running on port: 7881\n",
"Closing server running on port: 7871\n",
"Closing server running on port: 7881\n",
"Closing server running on port: 7861\n",
"Closing server running on port: 7876\n",
"Closing server running on port: 7878\n",
"Closing server running on port: 7883\n",
"Closing server running on port: 7874\n",
"Closing server running on port: 7864\n",
"Closing server running on port: 7862\n",
"Closing server running on port: 7877\n",
"Closing server running on port: 7873\n",
"Closing server running on port: 7879\n",
"Closing server running on port: 7866\n",
"Closing server running on port: 7875\n",
"Closing server running on port: 7874\n",
"Closing server running on port: 7865\n",
"Closing server running on port: 7872\n",
"Closing server running on port: 7861\n",
"Closing server running on port: 7862\n",
"Closing server running on port: 7864\n",
"Closing server running on port: 7880\n"
]
}
],
"source": [
"gr.close_all()"
]
},
{
"cell_type": "code",
"execution_count": 138,
"id": "efd8e5b3",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Closing server running on port: 7892\n"
]
}
],
"source": [
"app.close()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "29d9ea46",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.5"
}
},
"nbformat": 4,
"nbformat_minor": 5
}