Machine learning submission

author.json

@@ -1,4 +1,8 @@
 {
-  "name": "",
-  "entry_number": ""
+  "name": "Aditya Saxena",
+  "entry_number": "2022AM11218",
+  "discord_id" : "adityaaa2511",
+  "phone no": "9711366368",
+  "email id": "[email protected]",
+  "email id": "[email protected]",
 }

machine-learning/week2/data.yaml

@@ -0,0 +1,7 @@
+train: data_images/train
+val: data_images/text
+nc: 3
+names: ['person',
+        'car',
+        'bus'
+]

machine-learning/week2/yolo_predictions.ipynb

@@ -0,0 +1,244 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "1e2c1523",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: PyYAML in c:\\users\\adity\\onedrive\\desktop\\ml project week 2\\yolo_venv\\lib\\site-packages (6.0)\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install PyYAML"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "f403f869",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import cv2\n",
+    "import numpy as np\n",
+    "import os\n",
+    "import yaml\n",
+    "from yaml.loader import SafeLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "6588072b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['person', 'car', 'bus']\n"
+     ]
+    }
+   ],
+   "source": [
+    "with open('data.yaml',mode='r') as f:\n",
+    "    data_yaml=yaml.load(f,Loader=SafeLoader)\n",
+    "\n",
+    "label=data_yaml['names']\n",
+    "print(label)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "c4562cb7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Load Yolo Model\n",
+    "yolo=cv2.dnn.readNetFromONNX('./Model2/weights/best.onnx')\n",
+    "yolo.setPreferableBackend(cv2.dnn.DNN_BACKEND_OPENCV)\n",
+    "yolo.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "1ee09254",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Load the image\n",
+    "img=cv2.imread('./14474517749_600f20185e_c.jpg')\n",
+    "image=img.copy()\n",
+    "row,col,d=image.shape\n",
+    "\n",
+    "#get YOLO predictions\n",
+    "#step-1:-convert image into square image(array)\n",
+    "max_rc=max(row,col)\n",
+    "input_image=np.zeros((max_rc,max_rc,3),dtype=np.uint8)\n",
+    "input_image[0:row,0:col]=image\n",
+    "#step2:- get prediction from square array\n",
+    "INPUT_WH_YOLO=640\n",
+    "blob=cv2.dnn.blobFromImage(input_image,1/255,(INPUT_WH_YOLO,INPUT_WH_YOLO),swapRB=True,crop=False)\n",
+    "yolo.setInput(blob)\n",
+    "preds=yolo.forward()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "09278889",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(1, 25200, 8)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(preds.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "652c5418",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Non Maximum Suppression\n",
+    "#step-1:- filter detection based on confidence(0.4) and probability(0.25)\n",
+    "detections=preds[0]\n",
+    "boxes=[]\n",
+    "confidences=[]\n",
+    "classes=[]\n",
+    "#width and height of input image\n",
+    "image_w,image_h=input_image.shape[:2]\n",
+    "x_factor=image_w/INPUT_WH_YOLO\n",
+    "y_factor=image_h/INPUT_WH_YOLO\n",
+    "\n",
+    "for i in range(len(detections)):\n",
+    "    row=detections[i]\n",
+    "    confidence=row[4]\n",
+    "    if confidence>0.4:\n",
+    "        class_score=row[5:].max()\n",
+    "        class_id=row[5:].argmax()\n",
+    "        \n",
+    "        if class_score>0.25:\n",
+    "            cx,cy,w,h=row[0:4]\n",
+    "            left=int((cx-0.5*w)*x_factor)\n",
+    "            top=int((cy-0.5*h)*y_factor)\n",
+    "            width=int(w*x_factor)\n",
+    "            height=int(h*y_factor)\n",
+    "            \n",
+    "            box=np.array([left,top,width,height])\n",
+    "            \n",
+    "            #append values to the list\n",
+    "            confidences.append(confidence)\n",
+    "            boxes.append(box)\n",
+    "            classes.append(class_id)\n",
+    "\n",
+    "#clean\n",
+    "boxes_np=np.array(boxes).tolist()\n",
+    "confidences_np=np.array(confidences).tolist()\n",
+    "\n",
+    "#NMS\n",
+    "index=cv2.dnn.NMSBoxes(boxes_np,confidences_np,0.25,0.45).flatten()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "040b6def",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([ 3, 16,  1, 13])"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "index"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "80d09058",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Draw bounding box\n",
+    "for ind in index:\n",
+    "    x,y,w,h=boxes_np[ind]\n",
+    "    bb_conf=int(confidences_np[ind]*100)\n",
+    "    classes_id=classes[ind]\n",
+    "    class_name=label[classes_id]\n",
+    "    \n",
+    "    text=f'{class_name}:{bb_conf}%'\n",
+    "    cv2.rectangle(image,(x,y),(x+w,y+h),(0,255,0),2)\n",
+    "    cv2.rectangle(image,(x,y-30),(x+w,y),(255,255,255),-1)\n",
+    "    cv2.putText(image,text,(x,y-10),cv2.FONT_HERSHEY_PLAIN,0.7,(0,0,0),1)\n",
+    "    \n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "ec61c7be",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cv2.imshow('yolo_prediction',image)\n",
+    "cv2.waitKey(0)\n",
+    "cv2.destroyAllWindows()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "90114aee",
+   "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": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

machine-learning/week3/Car detection using Haar Cascades.ipynb

@@ -0,0 +1,80 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "3b2db876",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "<>:17: SyntaxWarning: \"is\" with a literal. Did you mean \"==\"?\n",
+      "<>:17: SyntaxWarning: \"is\" with a literal. Did you mean \"==\"?\n",
+      "C:\\Users\\adity\\AppData\\Local\\Temp\\ipykernel_37336\\590239235.py:17: SyntaxWarning: \"is\" with a literal. Did you mean \"==\"?\n",
+      "  if cars is ():\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "import cv2\n",
+    "\n",
+    "# We point OpenCV's CascadeClassifier function to where our \n",
+    "# classifier (XML file format) is stored\n",
+    "car_classifier = cv2.CascadeClassifier('Haarcascades/haarcascade_car.xml')\n",
+    "\n",
+    "# Load our image then convert it to grayscale\n",
+    "image = cv2.imread('lambo1.jpg')\n",
+    "gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)\n",
+    "\n",
+    "# Our classifier returns the ROI of the detected car as a tuple\n",
+    "# It stores the top left coordinate and the bottom right coordiantes\n",
+    "cars = car_classifier.detectMultiScale(gray, 1.4, 2)\n",
+    "\n",
+    "# When no cars detected, car_classifier returns and empty tuple\n",
+    "if cars is ():\n",
+    "    print(\"No cars found\")\n",
+    "\n",
+    "# We iterate through our faces array and draw a rectangle\n",
+    "# over each car in cars\n",
+    "for (x,y,w,h) in cars:\n",
+    "    cv2.rectangle(image, (x,y), (x+w,y+h), (0,255,0), 2)\n",
+    "    cv2.imshow('Car Detection', image)\n",
+    "    cv2.waitKey(0)\n",
+    "    \n",
+    "cv2.destroyAllWindows()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "00a3561f",
+   "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": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}