rover_phase1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a6dbc744",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2021-10-04 22:23:12.957463: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA\n",
      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
     ]
    }
   ],
   "source": [
    "import tensorflow_hub as hub\n",
    "import cv2\n",
    "import numpy\n",
    "import tensorflow as tf\n",
    "import pandas as pd\n",
    "\n",
    "detector = tf.saved_model.load('efficientdet_lite2_detection_1')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "0df0d8bc",
   "metadata": {},
   "outputs": [],
   "source": [
    "labels = pd.read_csv('labels.csv',sep=';',index_col='ID')\n",
    "labels = labels['OBJECT (2017 REL.)']\n",
    "\n",
    "cap = cv2.VideoCapture(0)\n",
    "\n",
    "width = 512\n",
    "height = 512"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "eba979fe",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2021-10-04 22:23:32.889025: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:185] None of the MLIR Optimization Passes are enabled (registered 2)\n"
     ]
    },
    {
     "ename": "NameError",
     "evalue": "name 'img_boxes' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m/var/folders/30/z2drzbvs68lcyywsjrh62dbc0000gn/T/ipykernel_4913/223108354.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     38\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     39\u001b[0m     \u001b[0;31m#Display the resulting frame\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 40\u001b[0;31m     \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimshow\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'black and white'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mimg_boxes\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     41\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mcv2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwaitKey\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m&\u001b[0m \u001b[0;36m0xFF\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0mord\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'q'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     42\u001b[0m         \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mNameError\u001b[0m: name 'img_boxes' is not defined"
     ]
    }
   ],
   "source": [
    "while(True):\n",
    "    #Capture frame-by-frame\n",
    "    ret, frame = cap.read()\n",
    "    \n",
    "    #Resize to respect the input_shape\n",
    "    inp = cv2.resize(frame, (width , height ))\n",
    "\n",
    "    #Convert img to RGB\n",
    "    rgb = cv2.cvtColor(inp, cv2.COLOR_BGR2RGB)\n",
    "\n",
    "    #Is optional but i recommend (float convertion and convert img to tensor image)\n",
    "    rgb_tensor = tf.convert_to_tensor(rgb, dtype=tf.uint8)\n",
    "\n",
    "    #Add dims to rgb_tensor\n",
    "    rgb_tensor = tf.expand_dims(rgb_tensor, 0)\n",
    "    \n",
    "    #Run inference\n",
    "    boxes, scores, classes, num_detections = detector(rgb_tensor)\n",
    "    \n",
    "    pred_labels = classes.numpy().astype('int')[0]\n",
    "    \n",
    "    pred_labels = [labels[i] for i in pred_labels]\n",
    "    pred_boxes = boxes.numpy()[0].astype('int')\n",
    "    pred_scores = scores.numpy()[0]\n",
    "   \n",
    "   #loop throughout the detections and place a box around it  \n",
    "    for score, (ymin,xmin,ymax,xmax), label in zip(pred_scores, pred_boxes, pred_labels):\n",
    "        if score < 0.5:\n",
    "            continue\n",
    "            \n",
    "        score_txt = f'{100 * round(score,0)}'\n",
    "        img_boxes = cv2.rectangle(rgb,(xmin, ymax),(xmax, ymin),(0,255,0),1)      \n",
    "        font = cv2.FONT_HERSHEY_SIMPLEX\n",
    "        cv2.putText(img_boxes,label,(xmin, ymax-10), font, 0.5, (255,0,0), 1, cv2.LINE_AA)\n",
    "        cv2.putText(img_boxes,score_txt,(xmax, ymax-10), font, 0.5, (255,0,0), 1, cv2.LINE_AA)\n",
    "\n",
    "\n",
    "\n",
    "    #Display the resulting frame\n",
    "    cv2.imshow('black and white',img_boxes)\n",
    "    if cv2.waitKey(1) & 0xFF == ord('q'):\n",
    "        break\n",
    "\n",
    "# When everything done, release the capture\n",
    "cap.release()\n",
    "cv2.destroyAllWindows()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6051314e",
   "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": "3.8.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}