Add files via upload

YOLOV5.ipynb

@@ -0,0 +1,165 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c17ddb86",
+   "metadata": {},
+   "source": [
+    "# importing libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "45e74618",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "import cv2"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0911b20b",
+   "metadata": {},
+   "source": [
+    "# calling YOLOV5s (yolo v5 small) model using torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "27689332",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Model\n",
+    "model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # or yolov5m, yolov5l, yolov5x, custom\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "638d865d",
+   "metadata": {},
+   "source": [
+    "# reading video from the directory, processing the video and then writing the output video"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3c4ec705",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#cap = cv2.VideoCapture(0)\n",
+    "\n",
+    "# reading video\n",
+    "cap = cv2.VideoCapture('test1.mp4')\n",
+    "\n",
+    "# finding the height and width of the video frames\n",
+    "frame_width = int(cap.get(3))\n",
+    "frame_height = int(cap.get(4))\n",
+    "\n",
+    "# creating object to write video in AVI extension\n",
+    "out = cv2.VideoWriter('outpy1.avi',cv2.VideoWriter_fourcc('M','J','P','G'), 10, (frame_width,frame_height))\n",
+    "\n",
+    "while(True):\n",
+    "    \n",
+    "    # reading frame from the video\n",
+    "    ret, frame = cap.read()    \n",
+    "    \n",
+    "    # passing the read frames to the YOLOV5s model\n",
+    "    results = model(frame)\n",
+    "    \n",
+    "    # finding the x1,y1,x2,y2 coordinates and labels of the bounding boxes of the detected objects in the video from the result object\n",
+    "    cords = results.xyxy[0].numpy()\n",
+    "    \n",
+    "    # reading individual box data\n",
+    "    for c in cords:\n",
+    "        \n",
+    "        # finding coordinates and labels\n",
+    "        # x1 = c[0]\n",
+    "        # x2 = c[2]\n",
+    "        # x3 = c[1]\n",
+    "        # x4 = c[3]\n",
+    "        \n",
+    "        #creating points\n",
+    "        \n",
+    "        # point1\n",
+    "        p1 = (int(c[0]),int(c[1]))\n",
+    "        # point2 \n",
+    "        p2 = (int(c[2]),int(c[3]))\n",
+    "        \n",
+    "        # drawing bounding boxes/rectangles around the objects using found coordinates\n",
+    "        image = cv2.rectangle(frame, p1,p2, (36,255,12), 2)\n",
+    "        \n",
+    "        # putting text (labels) on the rectangle\n",
+    "        cv2.putText(image,results.names[int(c[5])], (int(c[0]), int(c[1])-10), cv2.FONT_HERSHEY_SIMPLEX, 1, (36,255,12), 2,lineType=cv2.LINE_AA)\n",
+    "\n",
+    "    # here writing the video using the out object that we have created above\n",
+    "    out.write(frame)\n",
+    "    \n",
+    "    if cv2.waitKey(1) & 0xFF == ord('q'):\n",
+    "        break\n",
+    "        \n",
+    "cap.release()\n",
+    "cv2.destroyAllWindows()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e3e1de33",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "965abaa8",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5f058eb5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "340db310",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.8.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

requirements.txt

@@ -0,0 +1,31 @@
+# pip install -r requirements.txt
+
+# base ----------------------------------------
+matplotlib>=3.2.2
+numpy>=1.18.5
+opencv-python>=4.1.2
+Pillow
+PyYAML>=5.3.1
+scipy>=1.4.1
+torch>=1.7.0
+torchvision>=0.8.1
+tqdm>=4.41.0
+
+# logging -------------------------------------
+tensorboard>=2.4.1
+# wandb
+
+# plotting ------------------------------------
+seaborn>=0.11.0
+pandas
+
+# export --------------------------------------
+# coremltools>=4.1
+# onnx>=1.9.0
+# scikit-learn==0.19.2  # for coreml quantization
+
+# extras --------------------------------------
+# Cython  # for pycocotools https://github.com/cocodataset/cocoapi/issues/172
+# pycocotools>=2.0  # COCO mAP
+# albumentations>=1.0.3
+thop  # FLOPs computation