Photovoltaic_Fault_Detector/Code_Example/Example Detection AllInOne.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import time\n",
    "import os\n",
    "import argparse\n",
    "import json\n",
    "import cv2\n",
    "import sys\n",
    "sys.path += [os.path.abspath('../keras-yolo3-master')]\n",
    "\n",
    "from utils.utils import get_yolo_boxes, makedirs\n",
    "from utils.bbox import draw_boxes\n",
    "from tensorflow.keras.models import load_model\n",
    "from tqdm import tqdm\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from panel_disconnect import disconnect\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Define Image Path and output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_path   = '../images/Mision 23_DJI_0061.jpg' \n",
    "output_path  = 'Result_Complete_Example/'\n",
    "makedirs(output_path)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Load Model (Panel Detector, Soiling, Diode, Cell Damage)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:No training configuration found in save file: the model was *not* compiled. Compile it manually.\n",
      "WARNING:tensorflow:No training configuration found in save file: the model was *not* compiled. Compile it manually.\n",
      "WARNING:tensorflow:No training configuration found in save file: the model was *not* compiled. Compile it manually.\n",
      "WARNING:tensorflow:No training configuration found in save file: the model was *not* compiled. Compile it manually.\n"
     ]
    }
   ],
   "source": [
    "## Config of trained model, change this for use different trained model\n",
    "config_path_panel  = 'config_full_yolo_panel_infer.json' #Panel\n",
    "config_path_soiling  = 'config_full_yolo_fault_1_infer.json' #Soiling\n",
    "config_path_diode  = 'config_full_yolo_fault_4_infer.json'  #Diode\n",
    "config_path_cellD  = 'config_full_yolo_fault_2_infer.json'  #Cell Damage\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "## Parameters of detection\n",
    "net_h, net_w = 416, 416 # a multiple of 32, the smaller the faster\n",
    "obj_thresh, nms_thresh, nms_thresh_panel = 0.5, 0.45, 0.3\n",
    "\n",
    "####################################################\n",
    "#####   Load the model Panel Detector  #############\n",
    "####################################################\n",
    "with open(config_path_panel) as config_buffer:\n",
    "        config_panel = json.load(config_buffer)\n",
    "\n",
    "os.environ['CUDA_VISIBLE_DEVICES'] = config_panel['train']['gpus']\n",
    "infer_model_panel = load_model(config_panel['train']['saved_weights_name'])\n",
    "\n",
    "####################################################\n",
    "#####   Load the model Soiling  #############\n",
    "####################################################\n",
    "with open(config_path_soiling) as config_buffer:\n",
    "        config_soiling = json.load(config_buffer)\n",
    "\n",
    "infer_model_soiling = load_model(config_soiling['train']['saved_weights_name'])\n",
    "\n",
    "####################################################\n",
    "#####   Load the model Diode  #############\n",
    "####################################################\n",
    "with open(config_path_diode) as config_buffer:\n",
    "        config_diode = json.load(config_buffer)\n",
    "\n",
    "infer_model_diode = load_model(config_diode['train']['saved_weights_name'])\n",
    "\n",
    "####################################################\n",
    "#####   Load the model Cell Damage  #############\n",
    "####################################################\n",
    "with open(config_path_cellD) as config_buffer:\n",
    "        config_cellD = json.load(config_buffer)\n",
    "\n",
    "infer_model_cellD = load_model(config_cellD['train']['saved_weights_name'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Load Image paths"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "image_paths = []\n",
    "\n",
    "if os.path.isdir(input_path):\n",
    "    for inp_file in os.listdir(input_path):\n",
    "        image_paths += [input_path + inp_file]\n",
    "else:\n",
    "    image_paths += [input_path]\n",
    "\n",
    "image_paths = [inp_file for inp_file in image_paths if (inp_file[-4:] in ['.jpg', '.png', 'JPEG'])]\n",
    "\n",
    "# the main loop\n",
    "times = []\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Detection of images"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "images/Mision 23_DJI_0061.jpg\n",
      "Elapsed time = 5.464144468307495\n"
     ]
    },
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 1152x1152 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "for image_path in image_paths:\n",
    "    image = cv2.imread(image_path)\n",
    "    print(image_path)\n",
    "    start = time.time()\n",
    "    # predict the bounding boxes\n",
    "    boxes_soiling = get_yolo_boxes(infer_model_soiling, [image], net_h, net_w, config_soiling['model']['anchors'], obj_thresh, nms_thresh)[0]\n",
    "    boxes_diode = get_yolo_boxes(infer_model_diode, [image], net_h, net_w, config_diode['model']['anchors'], obj_thresh, nms_thresh)[0]\n",
    "    boxes_cellD = get_yolo_boxes(infer_model_cellD, [image], net_h, net_w, config_cellD['model']['anchors'], obj_thresh, nms_thresh)[0]\n",
    "    boxes_panel = get_yolo_boxes(infer_model_panel, [image], net_h, net_w, config_panel['model']['anchors'], obj_thresh, nms_thresh_panel)[0]\n",
    "    boxes_panel = [box for box in boxes_panel if box.get_score() > obj_thresh]\n",
    "    boxes_disc = disconnect(image, boxes_panel, z_thresh = 1.8)\n",
    "    print('Elapsed time = {}'.format(time.time() - start))\n",
    "    times.append(time.time() - start)\n",
    "    # Draw boxes\n",
    "    draw_boxes(image, boxes_soiling, config_soiling['model']['labels'], obj_thresh, number_color = 0)\n",
    "    draw_boxes(image, boxes_diode, config_diode['model']['labels'], obj_thresh, number_color = 2)\n",
    "    draw_boxes(image, boxes_cellD, config_cellD['model']['labels'], obj_thresh, number_color = 4)\n",
    "    draw_boxes(image, boxes_disc, ['disc'], obj_thresh, number_color = 5)\n",
    "    \n",
    "    cv2.imwrite(output_path + image_path.split('/')[-1], np.uint8(image))\n",
    "    # write the image with bounding boxes to file\n",
    "    #plt.figure(figsize=(16, 16))\n",
    "    #plt.imshow(image)\n",
    "\n",
    "file = open(output_path + 'time.txt','w')\n",
    "file.write('Tiempo promedio:' + str(np.mean(times)))\n",
    "file.close()\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example One image"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "image_path = image_paths[55]\n",
    "\n",
    "image = cv2.imread(image_path)\n",
    "plt.figure(figsize=(12, 10))\n",
    "plt.imshow(image)\n",
    "print(image_path)\n",
    "\n",
    "start = time.time()\n",
    "# predict the bounding boxes\n",
    "boxes_soiling = get_yolo_boxes(infer_model_soiling, [image], net_h, net_w, config_soiling['model']['anchors'], obj_thresh, nms_thresh)[0]\n",
    "boxes_diode = get_yolo_boxes(infer_model_diode, [image], net_h, net_w, config_diode['model']['anchors'], obj_thresh, nms_thresh)[0]\n",
    "boxes_cellD = get_yolo_boxes(infer_model_cellD, [image], net_h, net_w, config_cellD['model']['anchors'], obj_thresh, nms_thresh)[0]\n",
    "boxes_panel = get_yolo_boxes(infer_model_panel, [image], net_h, net_w, config_panel['model']['anchors'], obj_thresh, nms_thresh_panel)[0]\n",
    "boxes_panel = [box for box in boxes_panel if box.get_score() > obj_thresh]\n",
    "boxes_disc = disconnect(image, boxes_panel, z_thresh = 1.8)\n",
    "print('Elapsed time = {}'.format(time.time() - start))\n",
    "times.append(time.time() - start)\n",
    "# Draw boxes\n",
    "draw_boxes(image, boxes_soiling, config_soiling['model']['labels'], obj_thresh, number_color = 0)\n",
    "draw_boxes(image, boxes_diode, config_diode['model']['labels'], obj_thresh, number_color = 2)\n",
    "draw_boxes(image, boxes_cellD, config_cellD['model']['labels'], obj_thresh, number_color = 4)\n",
    "draw_boxes(image, boxes_disc, ['disc'], obj_thresh, number_color = 5)\n",
    "\n",
    "print('Elapsed time = {}'.format(time.time() - start))\n",
    "times.append(time.time() - start)\n",
    "plt.figure(figsize=(12, 10))\n",
    "plt.imshow(image)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Type Fault\n",
    "## 1: Soiling Fault\n",
    "## 2: Affected Cell \n",
    "## 4: Diode Fault\n",
    "## disc: Panel Disconnected"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}