javier/Photovoltaic_Fault_Detector
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
5f7b3aec39e37f18e4f0c3f1145471ae0d204bf1
Photovoltaic_Fault_Detector/Panel_Detector_Fault_C.ipynb

1298 lines
99 KiB
Plaintext
Raw Normal View History

Fault_Detector
2020-02-04 17:48:13 -03:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Cargar el modelo ssd7 \n",
"(https://github.com/pierluigiferrari/ssd_keras#how-to-fine-tune-one-of-the-trained-models-on-your-own-dataset)\n",
"\n",
"Training del SSD7 (modelo reducido de SSD). Parámetros en config_7.json y descargar VGG_ILSVRC_16_layers_fc_reduced.h5\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using TensorFlow backend.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Training on: \t{'1': 1, '2': 2, '3': 3, '4': 4, '5': 5, '6': 6, '7': 7, '8': 8}\n",
"\n",
"WARNING:tensorflow:From /home/dl-desktop/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Colocations handled automatically by placer.\n",
"OK create model\n",
"\n",
"Loading pretrained weights VGG.\n",
"\n",
"WARNING:tensorflow:From /home/dl-desktop/Desktop/Rentadrone/ssd_keras-master/keras_loss_function/keras_ssd_loss.py:133: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use tf.cast instead.\n",
"WARNING:tensorflow:From /home/dl-desktop/Desktop/Rentadrone/ssd_keras-master/keras_loss_function/keras_ssd_loss.py:166: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use tf.cast instead.\n",
"__________________________________________________________________________________________________\n",
"Layer (type) Output Shape Param # Connected to \n",
"==================================================================================================\n",
"input_1 (InputLayer) (None, 400, 400, 3) 0 \n",
"__________________________________________________________________________________________________\n",
"identity_layer (Lambda) (None, 400, 400, 3) 0 input_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"input_mean_normalization (Lambd (None, 400, 400, 3) 0 identity_layer[0][0] \n",
"__________________________________________________________________________________________________\n",
"input_channel_swap (Lambda) (None, 400, 400, 3) 0 input_mean_normalization[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv1_1 (Conv2D) (None, 400, 400, 64) 1792 input_channel_swap[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv1_2 (Conv2D) (None, 400, 400, 64) 36928 conv1_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"pool1 (MaxPooling2D) (None, 200, 200, 64) 0 conv1_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2_1 (Conv2D) (None, 200, 200, 128 73856 pool1[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2_2 (Conv2D) (None, 200, 200, 128 147584 conv2_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"pool2 (MaxPooling2D) (None, 100, 100, 128 0 conv2_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv3_1 (Conv2D) (None, 100, 100, 256 295168 pool2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv3_2 (Conv2D) (None, 100, 100, 256 590080 conv3_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv3_3 (Conv2D) (None, 100, 100, 256 590080 conv3_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"pool3 (MaxPooling2D) (None, 50, 50, 256) 0 conv3_3[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv4_1 (Conv2D) (None, 50, 50, 512) 1180160 pool3[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv4_2 (Conv2D) (None, 50, 50, 512) 2359808 conv4_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv4_3 (Conv2D) (None, 50, 50, 512) 2359808 conv4_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"pool4 (MaxPooling2D) (None, 25, 25, 512) 0 conv4_3[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv5_1 (Conv2D) (None, 25, 25, 512) 2359808 pool4[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv5_2 (Conv2D) (None, 25, 25, 512) 2359808 conv5_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv5_3 (Conv2D) (None, 25, 25, 512) 2359808 conv5_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"pool5 (MaxPooling2D) (None, 25, 25, 512) 0 conv5_3[0][0] \n",
"__________________________________________________________________________________________________\n",
"fc6 (Conv2D) (None, 25, 25, 1024) 4719616 pool5[0][0] \n",
"__________________________________________________________________________________________________\n",
"fc7 (Conv2D) (None, 25, 25, 1024) 1049600 fc6[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv6_1 (Conv2D) (None, 25, 25, 256) 262400 fc7[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv6_padding (ZeroPadding2D) (None, 27, 27, 256) 0 conv6_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv6_2 (Conv2D) (None, 13, 13, 512) 1180160 conv6_padding[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv7_1 (Conv2D) (None, 13, 13, 128) 65664 conv6_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv7_padding (ZeroPadding2D) (None, 15, 15, 128) 0 conv7_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv7_2 (Conv2D) (None, 7, 7, 256) 295168 conv7_padding[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv8_1 (Conv2D) (None, 7, 7, 128) 32896 conv7_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv8_2 (Conv2D) (None, 5, 5, 256) 295168 conv8_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv9_1 (Conv2D) (None, 5, 5, 128) 32896 conv8_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv4_3_norm (L2Normalization) (None, 50, 50, 512) 512 conv4_3[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv9_2 (Conv2D) (None, 3, 3, 256) 295168 conv9_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv4_3_norm_mbox_conf (Conv2D) (None, 50, 50, 36) 165924 conv4_3_norm[0][0] \n",
"__________________________________________________________________________________________________\n",
"fc7_mbox_conf (Conv2D) (None, 25, 25, 54) 497718 fc7[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv6_2_mbox_conf (Conv2D) (None, 13, 13, 54) 248886 conv6_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv7_2_mbox_conf (Conv2D) (None, 7, 7, 54) 124470 conv7_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv8_2_mbox_conf (Conv2D) (None, 5, 5, 36) 82980 conv8_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv9_2_mbox_conf (Conv2D) (None, 3, 3, 36) 82980 conv9_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv4_3_norm_mbox_loc (Conv2D) (None, 50, 50, 16) 73744 conv4_3_norm[0][0] \n",
"__________________________________________________________________________________________________\n",
"fc7_mbox_loc (Conv2D) (None, 25, 25, 24) 221208 fc7[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv6_2_mbox_loc (Conv2D) (None, 13, 13, 24) 110616 conv6_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv7_2_mbox_loc (Conv2D) (None, 7, 7, 24) 55320 conv7_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv8_2_mbox_loc (Conv2D) (None, 5, 5, 16) 36880 conv8_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv9_2_mbox_loc (Conv2D) (None, 3, 3, 16) 36880 conv9_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv4_3_norm_mbox_conf_reshape (None, 10000, 9) 0 conv4_3_norm_mbox_conf[0][0] \n",
"__________________________________________________________________________________________________\n",
"fc7_mbox_conf_reshape (Reshape) (None, 3750, 9) 0 fc7_mbox_conf[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv6_2_mbox_conf_reshape (Resh (None, 1014, 9) 0 conv6_2_mbox_conf[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv7_2_mbox_conf_reshape (Resh (None, 294, 9) 0 conv7_2_mbox_conf[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv8_2_mbox_conf_reshape (Resh (None, 100, 9) 0 conv8_2_mbox_conf[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv9_2_mbox_conf_reshape (Resh (None, 36, 9) 0 conv9_2_mbox_conf[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv4_3_norm_mbox_priorbox (Anc (None, 50, 50, 4, 8) 0 conv4_3_norm_mbox_loc[0][0] \n",
"__________________________________________________________________________________________________\n",
"fc7_mbox_priorbox (AnchorBoxes) (None, 25, 25, 6, 8) 0 fc7_mbox_loc[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv6_2_mbox_priorbox (AnchorBo (None, 13, 13, 6, 8) 0 conv6_2_mbox_loc[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv7_2_mbox_priorbox (AnchorBo (None, 7, 7, 6, 8) 0 conv7_2_mbox_loc[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv8_2_mbox_priorbox (AnchorBo (None, 5, 5, 4, 8) 0 conv8_2_mbox_loc[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv9_2_mbox_priorbox (AnchorBo (None, 3, 3, 4, 8) 0 conv9_2_mbox_loc[0][0] \n",
"__________________________________________________________________________________________________\n",
"mbox_conf (Concatenate) (None, 15194, 9) 0 conv4_3_norm_mbox_conf_reshape[0]\n",
" fc7_mbox_conf_reshape[0][0] \n",
" conv6_2_mbox_conf_reshape[0][0] \n",
" conv7_2_mbox_conf_reshape[0][0] \n",
" conv8_2_mbox_conf_reshape[0][0] \n",
" conv9_2_mbox_conf_reshape[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv4_3_norm_mbox_loc_reshape ( (None, 10000, 4) 0 conv4_3_norm_mbox_loc[0][0] \n",
"__________________________________________________________________________________________________\n",
"fc7_mbox_loc_reshape (Reshape) (None, 3750, 4) 0 fc7_mbox_loc[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv6_2_mbox_loc_reshape (Resha (None, 1014, 4) 0 conv6_2_mbox_loc[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv7_2_mbox_loc_reshape (Resha (None, 294, 4) 0 conv7_2_mbox_loc[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv8_2_mbox_loc_reshape (Resha (None, 100, 4) 0 conv8_2_mbox_loc[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv9_2_mbox_loc_reshape (Resha (None, 36, 4) 0 conv9_2_mbox_loc[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv4_3_norm_mbox_priorbox_resh (None, 10000, 8) 0 conv4_3_norm_mbox_priorbox[0][0] \n",
"__________________________________________________________________________________________________\n",
"fc7_mbox_priorbox_reshape (Resh (None, 3750, 8) 0 fc7_mbox_priorbox[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv6_2_mbox_priorbox_reshape ( (None, 1014, 8) 0 conv6_2_mbox_priorbox[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv7_2_mbox_priorbox_reshape ( (None, 294, 8) 0 conv7_2_mbox_priorbox[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv8_2_mbox_priorbox_reshape ( (None, 100, 8) 0 conv8_2_mbox_priorbox[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv9_2_mbox_priorbox_reshape ( (None, 36, 8) 0 conv9_2_mbox_priorbox[0][0] \n",
"__________________________________________________________________________________________________\n",
"mbox_conf_softmax (Activation) (None, 15194, 9) 0 mbox_conf[0][0] \n",
"__________________________________________________________________________________________________\n",
"mbox_loc (Concatenate) (None, 15194, 4) 0 conv4_3_norm_mbox_loc_reshape[0][\n",
" fc7_mbox_loc_reshape[0][0] \n",
" conv6_2_mbox_loc_reshape[0][0] \n",
" conv7_2_mbox_loc_reshape[0][0] \n",
" conv8_2_mbox_loc_reshape[0][0] \n",
" conv9_2_mbox_loc_reshape[0][0] \n",
"__________________________________________________________________________________________________\n",
"mbox_priorbox (Concatenate) (None, 15194, 8) 0 conv4_3_norm_mbox_priorbox_reshap\n",
" fc7_mbox_priorbox_reshape[0][0] \n",
" conv6_2_mbox_priorbox_reshape[0][\n",
" conv7_2_mbox_priorbox_reshape[0][\n",
" conv8_2_mbox_priorbox_reshape[0][\n",
" conv9_2_mbox_priorbox_reshape[0][\n",
"__________________________________________________________________________________________________\n",
"predictions (Concatenate) (None, 15194, 21) 0 mbox_conf_softmax[0][0] \n",
" mbox_loc[0][0] \n",
" mbox_priorbox[0][0] \n",
"==================================================================================================\n",
"Total params: 24,681,542\n",
"Trainable params: 24,681,542\n",
"Non-trainable params: 0\n",
"__________________________________________________________________________________________________\n"
]
}
],
"source": [
"from keras.optimizers import Adam, SGD\n",
"from keras.callbacks import ModelCheckpoint, LearningRateScheduler, TerminateOnNaN, CSVLogger\n",
"from keras import backend as K\n",
"from keras.models import load_model\n",
"from math import ceil\n",
"import numpy as np\n",
"from matplotlib import pyplot as plt\n",
"import os\n",
"import json\n",
"import xml.etree.cElementTree as ET\n",
"\n",
"import sys\n",
"sys.path += [os.path.abspath('../ssd_keras-master')]\n",
"\n",
"from keras_loss_function.keras_ssd_loss import SSDLoss\n",
"from keras_layers.keras_layer_AnchorBoxes import AnchorBoxes\n",
"from keras_layers.keras_layer_DecodeDetections import DecodeDetections\n",
"from keras_layers.keras_layer_DecodeDetectionsFast import DecodeDetectionsFast\n",
"from keras_layers.keras_layer_L2Normalization import L2Normalization\n",
"from ssd_encoder_decoder.ssd_input_encoder import SSDInputEncoder\n",
"from ssd_encoder_decoder.ssd_output_decoder import decode_detections, decode_detections_fast\n",
"from data_generator.object_detection_2d_data_generator import DataGenerator\n",
"from data_generator.object_detection_2d_geometric_ops import Resize\n",
"from data_generator.object_detection_2d_photometric_ops import ConvertTo3Channels\n",
"from data_generator.data_augmentation_chain_original_ssd import SSDDataAugmentation\n",
"from data_generator.object_detection_2d_misc_utils import apply_inverse_transforms\n",
"from eval_utils.average_precision_evaluator import Evaluator\n",
"from data_generator.data_augmentation_chain_variable_input_size import DataAugmentationVariableInputSize\n",
"from data_generator.data_augmentation_chain_constant_input_size import DataAugmentationConstantInputSize\n",
"\n",
"\n",
"def makedirs(path):\n",
" try:\n",
" os.makedirs(path)\n",
" except OSError:\n",
" if not os.path.isdir(path):\n",
" raise\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"K.tensorflow_backend._get_available_gpus()\n",
"\n",
"\n",
"def lr_schedule(epoch):\n",
" if epoch < 80:\n",
" return 0.001\n",
" elif epoch < 100:\n",
" return 0.0001\n",
" else:\n",
" return 0.00001\n",
"\n",
"config_path = 'config_300_fault_C.json'\n",
"\n",
"\n",
"with open(config_path) as config_buffer:\n",
" config = json.loads(config_buffer.read())\n",
"\n",
"###############################\n",
"# Parse the annotations\n",
"###############################\n",
"path_imgs_training = config['train']['train_image_folder']\n",
"path_anns_training = config['train']['train_annot_folder']\n",
"path_imgs_val = config['test']['test_image_folder']\n",
"path_anns_val = config['test']['test_annot_folder']\n",
"labels = config['model']['labels']\n",
"categories = {}\n",
"#categories = {\"Razor\": 1, \"Gun\": 2, \"Knife\": 3, \"Shuriken\": 4} #la categoría 0 es la background\n",
"for i in range(len(labels)): categories[labels[i]] = i+1\n",
"print('\\nTraining on: \\t' + str(categories) + '\\n')\n",
"\n",
"####################################\n",
"# Parameters\n",
"###################################\n",
" #%%\n",
"img_height = config['model']['input'] # Height of the model input images\n",
"img_width = config['model']['input'] # Width of the model input images\n",
"img_channels = 3 # Number of color channels of the model input images\n",
"mean_color = [123, 117, 104] # The per-channel mean of the images in the dataset. Do not change this value if you're using any of the pre-trained weights.\n",
"swap_channels = [2, 1, 0] # The color channel order in the original SSD is BGR, so we'll have the model reverse the color channel order of the input images.\n",
"n_classes = len(labels) # Number of positive classes, e.g. 20 for Pascal VOC, 80 for MS COCO\n",
"scales_pascal = [0.01, 0.05, 0.1, 0.2, 0.37, 0.54, 0.71] # The anchor box scaling factors used in the original SSD300 for the Pascal VOC datasets\n",
"#scales_coco = [0.07, 0.15, 0.33, 0.51, 0.69, 0.87, 1.05] # The anchor box scaling factors used in the original SSD300 for the MS COCO datasets\n",
"scales = scales_pascal\n",
"aspect_ratios = [[1.0, 2.0, 0.5],\n",
" [1.0, 2.0, 0.5, 3.0, 1.0/3.0],\n",
" [1.0, 2.0, 0.5, 3.0, 1.0/3.0],\n",
" [1.0, 2.0, 0.5, 3.0, 1.0/3.0],\n",
" [1.0, 2.0, 0.5],\n",
" [1.0, 2.0, 0.5]] # The anchor box aspect ratios used in the original SSD300; the order matters\n",
"two_boxes_for_ar1 = True\n",
"steps = [8, 16, 32, 64, 100, 300] # The space between two adjacent anchor box center points for each predictor layer.\n",
"offsets = [0.5, 0.5, 0.5, 0.5, 0.5, 0.5] # The offsets of the first anchor box center points from the top and left borders of the image as a fraction of the step size for each predictor layer.\n",
"clip_boxes = False # Whether or not to clip the anchor boxes to lie entirely within the image boundaries\n",
"variances = [0.1, 0.1, 0.2, 0.2] # The variances by which the encoded target coordinates are divided as in the original implementation\n",
"normalize_coords = True\n",
"\n",
"K.clear_session() # Clear previous models from memory.\n",
"\n",
"\n",
"model_path = config['train']['saved_weights_name']\n",
"# 3: Instantiate an optimizer and the SSD loss function and compile the model.\n",
"# If you want to follow the original Caffe implementation, use the preset SGD\n",
"# optimizer, otherwise I'd recommend the commented-out Adam optimizer.\n",
"\n",
"\n",
"if config['model']['backend'] == 'ssd7':\n",
" #weights_path = 'VGG_ILSVRC_16_layers_fc_reduced.h5'\n",
" scales = [0.08, 0.16, 0.32, 0.64, 0.96] # An explicit list of anchor box scaling factors. If this is passed, it will override `min_scale` and `max_scale`.\n",
" aspect_ratios = [0.5 ,1.0, 2.0] # The list of aspect ratios for the anchor boxes\n",
" two_boxes_for_ar1 = True # Whether or not you want to generate two anchor boxes for aspect ratio 1\n",
" steps = None # In case you'd like to set the step sizes for the anchor box grids manually; not recommended\n",
" offsets = None\n",
"\n",
"if os.path.exists(model_path):\n",
" print(\"\\nLoading pretrained weights.\\n\")\n",
" # We need to create an SSDLoss object in order to pass that to the model loader.\n",
" ssd_loss = SSDLoss(neg_pos_ratio=3, alpha=1.0)\n",
"\n",
" K.clear_session() # Clear previous models from memory.\n",
" model = load_model(model_path, custom_objects={'AnchorBoxes': AnchorBoxes,\n",
" 'L2Normalization': L2Normalization,\n",
" 'compute_loss': ssd_loss.compute_loss})\n",
"\n",
"\n",
"else:\n",
" ####################################\n",
" # Build the Keras model.\n",
" ###################################\n",
"\n",
" if config['model']['backend'] == 'ssd300':\n",
" #weights_path = 'VGG_VOC0712Plus_SSD_300x300_ft_iter_160000.h5'\n",
" from models.keras_ssd300 import ssd_300 as ssd\n",
"\n",
" model = ssd(image_size=(img_height, img_width, img_channels),\n",
" n_classes=n_classes,\n",
" mode='training',\n",
" l2_regularization=0.0005,\n",
" scales=scales,\n",
" aspect_ratios_per_layer=aspect_ratios,\n",
" two_boxes_for_ar1=two_boxes_for_ar1,\n",
" steps=steps,\n",
" offsets=offsets,\n",
" clip_boxes=clip_boxes,\n",
" variances=variances,\n",
" normalize_coords=normalize_coords,\n",
" subtract_mean=mean_color,\n",
" swap_channels=swap_channels)\n",
"\n",
"\n",
" elif config['model']['backend'] == 'ssd7':\n",
" #weights_path = 'VGG_ILSVRC_16_layers_fc_reduced.h5'\n",
" from models.keras_ssd7 import build_model as ssd\n",
" scales = [0.08, 0.16, 0.32, 0.64, 0.96] # An explicit list of anchor box scaling factors. If this is passed, it will override `min_scale` and `max_scale`.\n",
" aspect_ratios = [0.5 ,1.0, 2.0] # The list of aspect ratios for the anchor boxes\n",
" two_boxes_for_ar1 = True # Whether or not you want to generate two anchor boxes for aspect ratio 1\n",
" steps = None # In case you'd like to set the step sizes for the anchor box grids manually; not recommended\n",
" offsets = None\n",
" model = ssd(image_size=(img_height, img_width, img_channels),\n",
" n_classes=n_classes,\n",
" mode='training',\n",
" l2_regularization=0.0005,\n",
" scales=scales,\n",
" aspect_ratios_global=aspect_ratios,\n",
" aspect_ratios_per_layer=None,\n",
" two_boxes_for_ar1=two_boxes_for_ar1,\n",
" steps=steps,\n",
" offsets=offsets,\n",
" clip_boxes=clip_boxes,\n",
" variances=variances,\n",
" normalize_coords=normalize_coords,\n",
" subtract_mean=None,\n",
" divide_by_stddev=None)\n",
"\n",
" else :\n",
" print('Wrong Backend')\n",
"\n",
"\n",
"\n",
" print('OK create model')\n",
" #sgd = SGD(lr=config['train']['learning_rate'], momentum=0.9, decay=0.0, nesterov=False)\n",
"\n",
" # TODO: Set the path to the weights you want to load. only for ssd300 or ssd512\n",
"\n",
" weights_path = '../ssd_keras-master/VGG_ILSVRC_16_layers_fc_reduced.h5'\n",
" print(\"\\nLoading pretrained weights VGG.\\n\")\n",
" model.load_weights(weights_path, by_name=True)\n",
"\n",
" # 3: Instantiate an optimizer and the SSD loss function and compile the model.\n",
" # If you want to follow the original Caffe implementation, use the preset SGD\n",
" # optimizer, otherwise I'd recommend the commented-out Adam optimizer.\n",
"\n",
"\n",
" #adam = Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)\n",
" #sgd = SGD(lr=0.001, momentum=0.9, decay=0.0, nesterov=False)\n",
" optimizer = Adam(lr=config['train']['learning_rate'], beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)\n",
" ssd_loss = SSDLoss(neg_pos_ratio=3, alpha=1.0)\n",
" model.compile(optimizer=optimizer, loss=ssd_loss.compute_loss)\n",
"\n",
" model.summary()\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Instanciar los generadores de datos y entrenamiento del modelo.\n",
"\n",
"*Cambio realizado para leer png y jpg. keras-ssd-master/data_generator/object_detection_2d_data_generator.py función parse_xml\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"Processing image set 'train.txt': 0%| | 0/1337 [00:00<?, ?it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 4%|▍ | 51/1337 [00:00<00:02, 500.22it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 6%|▋ | 85/1337 [00:00<00:02, 436.14it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 9%|▊ | 114/1337 [00:00<00:03, 378.69it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 12%|█▏ | 155/1337 [00:00<00:03, 381.02it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 14%|█▎ | 183/1337 [00:00<00:03, 332.28it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 16%|█▌ | 216/1337 [00:00<00:03, 330.74it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 19%|█▉ | 259/1337 [00:00<00:03, 351.77it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 23%|██▎ | 309/1337 [00:00<00:02, 385.14it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 27%|██▋ | 357/1337 [00:00<00:02, 408.98it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 30%|███ | 404/1337 [00:01<00:02, 424.53it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 34%|███▍ | 456/1337 [00:01<00:01, 449.12it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 39%|███▊ | 515/1337 [00:01<00:01, 483.38it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 43%|████▎ | 580/1337 [00:01<00:01, 522.38it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 47%|████▋ | 634/1337 [00:01<00:01, 458.51it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 52%|█████▏ | 689/1337 [00:01<00:01, 482.17it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 56%|█████▌ | 746/1337 [00:01<00:01, 505.10it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 60%|██████ | 806/1337 [00:01<00:01, 529.93it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 65%|██████▌ | 875/1337 [00:01<00:00, 568.41it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 71%|███████ | 949/1337 [00:01<00:00, 609.51it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 77%|███████▋ | 1028/1337 [00:02<00:00, 652.57it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 82%|████████▏ | 1101/1337 [00:02<00:00, 673.91it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 88%|████████▊ | 1171/1337 [00:02<00:00, 650.52it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 93%|█████████▎| 1247/1337 [00:02<00:00, 678.71it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 99%|█████████▊| 1317/1337 [00:02<00:00, 663.80it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'train.txt': 100%|██████████| 1337/1337 [00:02<00:00, 522.70it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'test.txt': 0%| | 0/214 [00:00<?, ?it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'test.txt': 24%|██▍ | 52/214 [00:00<00:00, 515.59it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'test.txt': 43%|████▎ | 91/214 [00:00<00:00, 470.10it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'test.txt': 68%|██████▊ | 145/214 [00:00<00:00, 487.29it/s]\u001b[A\u001b[A\n",
"\n",
"Processing image set 'test.txt': 100%|██████████| 214/214 [00:00<00:00, 530.50it/s]\u001b[A\u001b[A1 : 2260\n",
"2 : 112\n",
"3 : 98\n",
"4 : 925\n",
"5 : 25\n",
"7 : 46\n",
"Number of images in the training dataset:\t 1337\n",
"Number of images in the validation dataset:\t 214\n"
]
},
{
"ename": "OSError",
"evalue": "cannot identify image file 'Train&Test_C/images/Mision 22_DJI_0067.jpg'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mOSError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-10-c3fc22ec5bc6>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 187\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 188\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 189\u001b[0;31m \u001b[0mbatch_images\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch_labels\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrain_generator\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 190\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 191\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/Desktop/Rentadrone/ssd_keras-master/data_generator/object_detection_2d_data_generator.py\u001b[0m in \u001b[0;36mgenerate\u001b[0;34m(self, batch_size, shuffle, transformations, label_encoder, returns, keep_images_without_gt, degenerate_box_handling)\u001b[0m\n\u001b[1;32m 1019\u001b[0m \u001b[0mbatch_filenames\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfilenames\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mcurrent\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mcurrent\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mbatch_size\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1020\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mfilename\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mbatch_filenames\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1021\u001b[0;31m \u001b[0;32mwith\u001b[0m \u001b[0mImage\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mimage\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 1022\u001b[0m \u001b[0mbatch_X\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0muint8\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 1023\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/PIL/Image.py\u001b[0m in \u001b[0;36mopen\u001b[0;34m(fp, mode)\u001b[0m\n\u001b[1;32m 2703\u001b[0m \u001b[0mwarnings\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwarn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmessage\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2704\u001b[0m raise IOError(\"cannot identify image file %r\"\n\u001b[0;32m-> 2705\u001b[0;31m % (filename if filename else fp))\n\u001b[0m\u001b[1;32m 2706\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2707\u001b[0m \u001b[0;31m#\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mOSError\u001b[0m: cannot identify image file 'Train&Test_C/images/Mision 22_DJI_0067.jpg'"
]
}
],
"source": [
"#ENTRENAMIENTO DE MODELO\n",
"#####################################################################\n",
"# Instantiate two `DataGenerator` objects: One for training, one for validation.\n",
"######################################################################\n",
"# Optional: If you have enough memory, consider loading the images into memory for the reasons explained above.\n",
"\n",
"train_dataset = DataGenerator(load_images_into_memory=False, hdf5_dataset_path=None)\n",
"val_dataset = DataGenerator(load_images_into_memory=False, hdf5_dataset_path=None)\n",
"\n",
"# 2: Parse the image and label lists for the training and validation datasets. This can take a while.\n",
"\n",
"\n",
"\n",
"# The XML parser needs to now what object class names to look for and in which order to map them to integers.\n",
"classes = ['background' ] + labels\n",
"\n",
"train_dataset.parse_xml(images_dirs= [config['train']['train_image_folder']],\n",
" image_set_filenames=[config['train']['train_image_set_filename']],\n",
" annotations_dirs=[config['train']['train_annot_folder']],\n",
" classes=classes,\n",
" include_classes='all',\n",
" #classes = classes, \n",
" #include_classes= [1],\n",
" exclude_truncated=False,\n",
" exclude_difficult=False,\n",
" ret=False)\n",
"\n",
"val_dataset.parse_xml(images_dirs= [config['test']['test_image_folder']],\n",
" image_set_filenames=[config['test']['test_image_set_filename']],\n",
" annotations_dirs=[config['test']['test_annot_folder']],\n",
" classes=classes,\n",
" include_classes='all',\n",
" #classes = classes, \n",
" #include_classes=[1],\n",
" exclude_truncated=False,\n",
" exclude_difficult=False,\n",
" ret=False)\n",
"\n",
"#########################\n",
"# 3: Set the batch size.\n",
"#########################\n",
"batch_size = config['train']['batch_size'] # Change the batch size if you like, or if you run into GPU memory issues.\n",
"\n",
"##########################\n",
"# 4: Set the image transformations for pre-processing and data augmentation options.\n",
"##########################\n",
"# For the training generator:\n",
"\n",
"\n",
"# For the validation generator:\n",
"convert_to_3_channels = ConvertTo3Channels()\n",
"resize = Resize(height=img_height, width=img_width)\n",
"\n",
"######################################3\n",
"# 5: Instantiate an encoder that can encode ground truth labels into the format needed by the SSD loss function.\n",
"#########################################\n",
"# The encoder constructor needs the spatial dimensions of the model's predictor layers to create the anchor boxes.\n",
"if config['model']['backend'] == 'ssd300':\n",
" predictor_sizes = [model.get_layer('conv4_3_norm_mbox_conf').output_shape[1:3],\n",
" model.get_layer('fc7_mbox_conf').output_shape[1:3],\n",
" model.get_layer('conv6_2_mbox_conf').output_shape[1:3],\n",
" model.get_layer('conv7_2_mbox_conf').output_shape[1:3],\n",
" model.get_layer('conv8_2_mbox_conf').output_shape[1:3],\n",
" model.get_layer('conv9_2_mbox_conf').output_shape[1:3]]\n",
" ssd_input_encoder = SSDInputEncoder(img_height=img_height,\n",
" img_width=img_width,\n",
" n_classes=n_classes,\n",
" predictor_sizes=predictor_sizes,\n",
" scales=scales,\n",
" aspect_ratios_per_layer=aspect_ratios,\n",
" two_boxes_for_ar1=two_boxes_for_ar1,\n",
" steps=steps,\n",
" offsets=offsets,\n",
" clip_boxes=clip_boxes,\n",
" variances=variances,\n",
" matching_type='multi',\n",
" pos_iou_threshold=0.5,\n",
" neg_iou_limit=0.5,\n",
" normalize_coords=normalize_coords)\n",
"\n",
"elif config['model']['backend'] == 'ssd7':\n",
" predictor_sizes = [model.get_layer('classes4').output_shape[1:3],\n",
" model.get_layer('classes5').output_shape[1:3],\n",
" model.get_layer('classes6').output_shape[1:3],\n",
" model.get_layer('classes7').output_shape[1:3]]\n",
" ssd_input_encoder = SSDInputEncoder(img_height=img_height,\n",
" img_width=img_width,\n",
" n_classes=n_classes,\n",
" predictor_sizes=predictor_sizes,\n",
" scales=scales,\n",
" aspect_ratios_global=aspect_ratios,\n",
" two_boxes_for_ar1=two_boxes_for_ar1,\n",
" steps=steps,\n",
" offsets=offsets,\n",
" clip_boxes=clip_boxes,\n",
" variances=variances,\n",
" matching_type='multi',\n",
" pos_iou_threshold=0.5,\n",
" neg_iou_limit=0.3,\n",
" normalize_coords=normalize_coords)\n",
"\n",
"\n",
"\n",
" \n",
"data_augmentation_chain = DataAugmentationVariableInputSize(resize_height = img_height,\n",
" resize_width = img_width,\n",
" random_brightness=(-48, 48, 0.5),\n",
" random_contrast=(0.5, 1.8, 0.5),\n",
" random_saturation=(0.5, 1.8, 0.5),\n",
" random_hue=(18, 0.5),\n",
" random_flip=0.5,\n",
" n_trials_max=3,\n",
" clip_boxes=True,\n",
" overlap_criterion='area',\n",
" bounds_box_filter=(0.3, 1.0),\n",
" bounds_validator=(0.5, 1.0),\n",
" n_boxes_min=1,\n",
" background=(0,0,0))\n",
"#######################\n",
"# 6: Create the generator handles that will be passed to Keras' `fit_generator()` function.\n",
"#######################\n",
"\n",
"train_generator = train_dataset.generate(batch_size=batch_size,\n",
" shuffle=True,\n",
" transformations= [data_augmentation_chain],\n",
" label_encoder=ssd_input_encoder,\n",
" returns={'processed_images',\n",
" 'encoded_labels'},\n",
" keep_images_without_gt=False)\n",
"\n",
"val_generator = val_dataset.generate(batch_size=batch_size,\n",
" shuffle=False,\n",
" transformations=[convert_to_3_channels,\n",
" resize],\n",
" label_encoder=ssd_input_encoder,\n",
" returns={'processed_images',\n",
" 'encoded_labels'},\n",
" keep_images_without_gt=False)\n",
"\n",
"# Summary instance training\n",
"category_train_list = []\n",
"for image_label in train_dataset.labels:\n",
" category_train_list += [i[0] for i in image_label]\n",
"summary_category_training = {train_dataset.classes[i]: category_train_list.count(i) for i in list(set(category_train_list))}\n",
"for i in summary_category_training.keys():\n",
" print(i, ': {:.0f}'.format(summary_category_training[i]))\n",
"\n",
"\n",
"\n",
"# Get the number of samples in the training and validations datasets.\n",
"train_dataset_size = train_dataset.get_dataset_size()\n",
"val_dataset_size = val_dataset.get_dataset_size()\n",
"\n",
"print(\"Number of images in the training dataset:\\t{:>6}\".format(train_dataset_size))\n",
"print(\"Number of images in the validation dataset:\\t{:>6}\".format(val_dataset_size))\n",
"\n",
"\n",
"\n",
"##########################\n",
"# Define model callbacks.\n",
"#########################\n",
"\n",
"# TODO: Set the filepath under which you want to save the model.\n",
"model_checkpoint = ModelCheckpoint(filepath= config['train']['saved_weights_name'],\n",
" monitor='val_loss',\n",
" verbose=1,\n",
" save_best_only=True,\n",
" save_weights_only=False,\n",
" mode='auto',\n",
" period=1)\n",
"#model_checkpoint.best =\n",
"\n",
"csv_logger = CSVLogger(filename='log.csv',\n",
" separator=',',\n",
" append=True)\n",
"\n",
"learning_rate_scheduler = LearningRateScheduler(schedule=lr_schedule,\n",
" verbose=1)\n",
"\n",
"terminate_on_nan = TerminateOnNaN()\n",
"\n",
"callbacks = [model_checkpoint,\n",
" csv_logger,\n",
" learning_rate_scheduler,\n",
" terminate_on_nan]\n",
"\n",
"\n",
"\n",
"batch_images, batch_labels = next(train_generator)\n",
"\n",
"\n",
"initial_epoch = 0\n",
"final_epoch = 100 #config['train']['nb_epochs']\n",
"steps_per_epoch = 200\n",
"\n",
"history = model.fit_generator(generator=train_generator,\n",
" steps_per_epoch=steps_per_epoch,\n",
" epochs=final_epoch,\n",
" callbacks=callbacks,\n",
" validation_data=val_generator,\n",
" validation_steps=ceil(val_dataset_size/batch_size*10),\n",
" initial_epoch=initial_epoch,\n",
" verbose = 1 if config['train']['debug'] else 2)\n",
"\n",
"history_path = config['train']['saved_weights_name'].split('.')[0] + '_history'\n",
"\n",
"np.save(history_path, history.history)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['background', '1', '4']"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"classes"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"dict_keys(['val_loss', 'loss', 'lr'])\n"
]
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"experimento_ssd300_fault_C_1.h5\n"
]
}
],
"source": [
"#Graficar aprendizaje\n",
"\n",
"history_path =config['train']['saved_weights_name'].split('.')[0] + '_history'\n",
"\n",
"hist_load = np.load(history_path + '.npy',allow_pickle=True).item()\n",
"\n",
"print(hist_load.keys())\n",
"\n",
"# summarize history for loss\n",
"plt.plot(hist_load['loss'])\n",
"plt.plot(hist_load['val_loss'])\n",
"plt.title('model loss')\n",
"plt.ylabel('loss')\n",
"plt.xlabel('epoch')\n",
"plt.legend(['train', 'test'], loc='upper left')\n",
"plt.ylim((0, 10)) \n",
"plt.show()\n",
"\n",
"print(config['train']['saved_weights_name'])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Evaluación del Modelo"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Processing image set 'train.txt': 0%| | 0/1366 [00:00<?, ?it/s]\u001b[A\n",
"Processing image set 'train.txt': 4%|▍ | 56/1366 [00:00<00:02, 552.81it/s]\u001b[A\n",
"Processing image set 'train.txt': 7%|▋ | 100/1366 [00:00<00:02, 512.21it/s]\u001b[A\n",
"Processing image set 'train.txt': 10%|█ | 143/1366 [00:00<00:02, 475.06it/s]\u001b[A\n",
"Processing image set 'train.txt': 14%|█▍ | 192/1366 [00:00<00:02, 478.57it/s]\u001b[A\n",
"Processing image set 'train.txt': 19%|█▊ | 255/1366 [00:00<00:02, 515.69it/s]\u001b[A\n",
"Processing image set 'train.txt': 23%|██▎ | 315/1366 [00:00<00:01, 538.23it/s]\u001b[A\n",
"Processing image set 'train.txt': 27%|██▋ | 364/1366 [00:00<00:02, 341.44it/s]\u001b[A\n",
"Processing image set 'train.txt': 30%|██▉ | 408/1366 [00:00<00:02, 365.28it/s]\u001b[A\n",
"Processing image set 'train.txt': 34%|███▎ | 461/1366 [00:01<00:02, 402.06it/s]\u001b[A\n",
"Processing image set 'train.txt': 38%|███▊ | 523/1366 [00:01<00:01, 448.07it/s]\u001b[A\n",
"Processing image set 'train.txt': 43%|████▎ | 582/1366 [00:01<00:01, 480.98it/s]\u001b[A\n",
"Processing image set 'train.txt': 47%|████▋ | 644/1366 [00:01<00:01, 514.29it/s]\u001b[A\n",
"Processing image set 'train.txt': 51%|█████ | 699/1366 [00:01<00:01, 452.24it/s]\u001b[A\n",
"Processing image set 'train.txt': 56%|█████▌ | 765/1366 [00:01<00:01, 498.72it/s]\u001b[A\n",
"Processing image set 'train.txt': 61%|██████ | 830/1366 [00:01<00:01, 534.12it/s]\u001b[A\n",
"Processing image set 'train.txt': 66%|██████▌ | 902/1366 [00:01<00:00, 578.77it/s]\u001b[A\n",
"Processing image set 'train.txt': 72%|███████▏ | 983/1366 [00:01<00:00, 632.15it/s]\u001b[A\n",
"Processing image set 'train.txt': 77%|███████▋ | 1057/1366 [00:02<00:00, 659.69it/s]\u001b[A\n",
"Processing image set 'train.txt': 83%|████████▎ | 1129/1366 [00:02<00:00, 676.69it/s]\u001b[A\n",
"Processing image set 'train.txt': 88%|████████▊ | 1199/1366 [00:02<00:00, 619.87it/s]\u001b[A\n",
"Processing image set 'train.txt': 93%|█████████▎| 1275/1366 [00:02<00:00, 654.72it/s]\u001b[A\n",
"Processing image set 'train.txt': 98%|█████████▊| 1343/1366 [00:02<00:00, 649.40it/s]\u001b[A\n",
"Processing image set 'train.txt': 100%|██████████| 1366/1366 [00:02<00:00, 539.87it/s]\u001b[A\n",
"Processing image set 'test.txt': 0%| | 0/190 [00:00<?, ?it/s]\u001b[A\n",
"Processing image set 'test.txt': 26%|██▌ | 49/190 [00:00<00:00, 480.51it/s]\u001b[A\n",
"Processing image set 'test.txt': 65%|██████▌ | 124/190 [00:00<00:00, 538.53it/s]\u001b[A\n",
"Processing image set 'test.txt': 100%|██████████| 190/190 [00:00<00:00, 674.96it/s]\u001b[ANumber of images in the evaluation dataset: 190\n",
"\n",
"\n",
" 0%| | 0/48 [00:00<?, ?it/s]\u001b[A\n",
"Producing predictions batch-wise: 0%| | 0/48 [00:00<?, ?it/s]\u001b[A"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-8-7b51ac359b0d>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 84\u001b[0m \u001b[0mreturn_recalls\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 85\u001b[0m \u001b[0mreturn_average_precisions\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 86\u001b[0;31m verbose=True)\n\u001b[0m\u001b[1;32m 87\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 88\u001b[0m \u001b[0mmean_average_precision\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maverage_precisions\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mprecisions\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrecalls\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mresults\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/Desktop/Rentadrone/ssd_keras-master/eval_utils/average_precision_evaluator.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, img_height, img_width, batch_size, data_generator_mode, round_confidences, matching_iou_threshold, border_pixels, sorting_algorithm, average_precision_mode, num_recall_points, ignore_neutral_boxes, return_precisions, return_recalls, return_average_precisions, verbose, decoding_confidence_thresh, decoding_iou_threshold, decoding_top_k, decoding_pred_coords, decoding_normalize_coords)\u001b[0m\n\u001b[1;32m 199\u001b[0m \u001b[0mround_confidences\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mround_confidences\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 200\u001b[0m \u001b[0mverbose\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mverbose\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 201\u001b[0;31m ret=False)\n\u001b[0m\u001b[1;32m 202\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 203\u001b[0m \u001b[0;31m#############################################################################################\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/Desktop/Rentadrone/ssd_keras-master/eval_utils/average_precision_evaluator.py\u001b[0m in \u001b[0;36mpredict_on_dataset\u001b[0;34m(self, img_height, img_width, batch_size, data_generator_mode, decoding_confidence_thresh, decoding_iou_threshold, decoding_top_k, decoding_pred_coords, decoding_normalize_coords, decoding_border_pixels, round_confidences, verbose, ret)\u001b[0m\n\u001b[1;32m 389\u001b[0m \u001b[0mimg_height\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mimg_height\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 390\u001b[0m \u001b[0mimg_width\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mimg_width\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 391\u001b[0;31m border_pixels=decoding_border_pixels)\n\u001b[0m\u001b[1;32m 392\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 393\u001b[0m \u001b[0;31m# Filter out the all-zeros dummy elements of `y_pred`.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/Desktop/Rentadrone/ssd_keras-master/ssd_encoder_decoder/ssd_output_decoder.py\u001b[0m in \u001b[0;36mdecode_detections\u001b[0;34m(y_pred, confidence_thresh, iou_threshold, top_k, input_coords, normalize_coords, img_height, img_width, border_pixels)\u001b[0m\n\u001b[1;32m 209\u001b[0m \u001b[0mthreshold_met\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msingle_class\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0msingle_class\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0mconfidence_thresh\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;31m# ...keep only those boxes with a confidence above the set threshold.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 210\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mthreshold_met\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;31m# If any boxes made the threshold...\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 211\u001b[0;31m \u001b[0mmaxima\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_greedy_nms\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mthreshold_met\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0miou_threshold\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0miou_threshold\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcoords\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'corners'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mborder_pixels\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mborder_pixels\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# ...perform NMS on them.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 212\u001b[0m \u001b[0mmaxima_output\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mzeros\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmaxima\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmaxima\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# Expand the last dimension by one element to have room for the class ID. This is now an arrray of shape `[n_boxes, 6]`\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 213\u001b[0m \u001b[0mmaxima_output\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mclass_id\u001b[0m \u001b[0;31m# Write the class ID to the first column...\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/Desktop/Rentadrone/ssd_keras-master/ssd_encoder_decoder/ssd_output_decoder.py\u001b[0m in \u001b[0;36m_greedy_nms\u001b[0;34m(predictions, iou_threshold, coords, border_pixels)\u001b[0m\n\u001b[1;32m 88\u001b[0m \u001b[0mboxes_left\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdelete\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mboxes_left\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmaximum_index\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# Now remove the maximum box from `boxes_left`\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 89\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mboxes_left\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;32mbreak\u001b[0m \u001b[0;31m# If there are no boxes left after this step, break. Otherwise...\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 90\u001b[0;31m \u001b[0msimilarities\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0miou\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mboxes_left\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmaximum_box\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcoords\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcoords\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'element-wise'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mborder_pixels\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mborder_pixels\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# ...compare (IoU) the other left over boxes to the maximum box...\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 91\u001b[0m \u001b[0mboxes_left\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mboxes_left\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0msimilarities\u001b[0m \u001b[0;34m<=\u001b[0m \u001b[0miou_threshold\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;31m# ...so that we can remove the ones that overlap too much with the maximum box\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 92\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmaxima\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/Desktop/Rentadrone/ssd_keras-master/bounding_box_utils/bounding_box_utils.py\u001b[0m in \u001b[0;36miou\u001b[0;34m(boxes1, boxes2, coords, mode, border_pixels)\u001b[0m\n\u001b[1;32m 343\u001b[0m \u001b[0;31m# Compute the interesection areas.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 344\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 345\u001b[0;31m \u001b[0mintersection_areas\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mintersection_area_\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mboxes1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mboxes2\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcoords\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcoords\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmode\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 346\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 347\u001b[0m \u001b[0mm\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mboxes1\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;31m# The number of boxes in `boxes1`\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/Desktop/Rentadrone/ssd_keras-master/bounding_box_utils/bounding_box_utils.py\u001b[0m in \u001b[0;36mintersection_area_\u001b[0;34m(boxes1, boxes2, coords, mode, border_pixels)\u001b[0m\n\u001b[1;32m 278\u001b[0m \u001b[0mside_lengths\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmaximum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmax_xy\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mmin_xy\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0md\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 279\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 280\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mside_lengths\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m*\u001b[0m \u001b[0mside_lengths\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m1\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 281\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 282\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"\n",
"config_path = 'config_7_fault_1.json'\n",
"\n",
"with open(config_path) as config_buffer:\n",
" config = json.loads(config_buffer.read())\n",
"\n",
" \n",
"model_mode = 'training'\n",
"# TODO: Set the path to the `.h5` file of the model to be loaded.\n",
"model_path = config['train']['saved_weights_name']\n",
"\n",
"# We need to create an SSDLoss object in order to pass that to the model loader.\n",
"ssd_loss = SSDLoss(neg_pos_ratio=3, alpha=1.0)\n",
"\n",
"K.clear_session() # Clear previous models from memory.\n",
"\n",
"model = load_model(model_path, custom_objects={'AnchorBoxes': AnchorBoxes,\n",
" 'L2Normalization': L2Normalization,\n",
" 'DecodeDetections': DecodeDetections,\n",
" 'compute_loss': ssd_loss.compute_loss})\n",
"\n",
"\n",
" \n",
"train_dataset = DataGenerator(load_images_into_memory=False, hdf5_dataset_path=None)\n",
"val_dataset = DataGenerator(load_images_into_memory=False, hdf5_dataset_path=None)\n",
"\n",
"# 2: Parse the image and label lists for the training and validation datasets. This can take a while.\n",
"\n",
"\n",
"\n",
"# The XML parser needs to now what object class names to look for and in which order to map them to integers.\n",
"classes = ['background' ] + labels\n",
"\n",
"train_dataset.parse_xml(images_dirs= [config['train']['train_image_folder']],\n",
" image_set_filenames=[config['train']['train_image_set_filename']],\n",
" annotations_dirs=[config['train']['train_annot_folder']],\n",
" classes=classes,\n",
" include_classes='all',\n",
" #classes = ['background', 'panel', 'cell'], \n",
" #include_classes=classes,\n",
" exclude_truncated=False,\n",
" exclude_difficult=False,\n",
" ret=False)\n",
"\n",
"val_dataset.parse_xml(images_dirs= [config['test']['test_image_folder']],\n",
" image_set_filenames=[config['test']['test_image_set_filename']],\n",
" annotations_dirs=[config['test']['test_annot_folder']],\n",
" classes=classes,\n",
" include_classes='all',\n",
" #classes = ['background', 'panel', 'cell'], \n",
" #include_classes=classes,\n",
" exclude_truncated=False,\n",
" exclude_difficult=False,\n",
" ret=False)\n",
"\n",
"#########################\n",
"# 3: Set the batch size.\n",
"#########################\n",
"batch_size = config['train']['batch_size'] # Change the batch size if you like, or if you run into GPU memory issues.\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"evaluator = Evaluator(model=model,\n",
" n_classes=n_classes,\n",
" data_generator=val_dataset,\n",
" model_mode='training')\n",
"\n",
"results = evaluator(img_height=img_height,\n",
" img_width=img_width,\n",
" batch_size=4,\n",
" data_generator_mode='resize',\n",
" round_confidences=False,\n",
" matching_iou_threshold=0.5,\n",
" border_pixels='include',\n",
" sorting_algorithm='quicksort',\n",
" average_precision_mode='sample',\n",
" num_recall_points=11,\n",
" ignore_neutral_boxes=True,\n",
" return_precisions=True,\n",
" return_recalls=True,\n",
" return_average_precisions=True,\n",
" verbose=True)\n",
"\n",
"mean_average_precision, average_precisions, precisions, recalls = results\n",
"total_instances = []\n",
"precisions = []\n",
"\n",
"for i in range(1, len(average_precisions)):\n",
" \n",
" print('{:.0f} instances of class'.format(len(recalls[i])),\n",
" classes[i], 'with average precision: {:.4f}'.format(average_precisions[i]))\n",
" total_instances.append(len(recalls[i]))\n",
" precisions.append(average_precisions[i])\n",
"\n",
"if sum(total_instances) == 0:\n",
" \n",
" print('No test instances found.')\n",
"\n",
"else:\n",
"\n",
" print('mAP using the weighted average of precisions among classes: {:.4f}'.format(sum([a * b for a, b in zip(total_instances, precisions)]) / sum(total_instances)))\n",
" print('mAP: {:.4f}'.format(sum(precisions) / sum(x > 0 for x in total_instances)))\n",
"\n",
" for i in range(1, len(average_precisions)):\n",
" print(\"{:<14}{:<6}{}\".format(classes[i], 'AP', round(average_precisions[i], 3)))\n",
" print()\n",
" print(\"{:<14}{:<6}{}\".format('','mAP', round(mean_average_precision, 3)))"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"24"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ceil(val_dataset_size/batch_size)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Cargar nuevamente el modelo desde los pesos.\n",
"Predicción"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Training on: \t{'1': 1, '2': 2, '3': 3, '4': 4, '5': 5, '6': 6, '7': 7, '8': 8}\n",
"\n"
]
}
],
"source": [
"from imageio import imread\n",
"from keras.preprocessing import image\n",
"import time\n",
"\n",
"config_path = 'config_7_fault_1.json'\n",
"input_path = ['fault_jpg/']\n",
"output_path = 'result_ssd7_fault_1/'\n",
"\n",
"with open(config_path) as config_buffer:\n",
" config = json.loads(config_buffer.read())\n",
"\n",
"makedirs(output_path)\n",
"###############################\n",
"# Parse the annotations\n",
"###############################\n",
"score_threshold = 0.2\n",
"score_threshold_iou = 0.2\n",
"labels = config['model']['labels']\n",
"categories = {}\n",
"#categories = {\"Razor\": 1, \"Gun\": 2, \"Knife\": 3, \"Shuriken\": 4} #la categoría 0 es la background\n",
"for i in range(len(labels)): categories[labels[i]] = i+1\n",
"print('\\nTraining on: \\t' + str(categories) + '\\n')\n",
"\n",
"img_height = config['model']['input'] # Height of the model input images\n",
"img_width = config['model']['input'] # Width of the model input images\n",
"img_channels = 3 # Number of color channels of the model input images\n",
"n_classes = len(labels) # Number of positive classes, e.g. 20 for Pascal VOC, 80 for MS COCO\n",
"classes = ['background'] + labels\n",
"\n",
"model_mode = 'training'\n",
"# TODO: Set the path to the `.h5` file of the model to be loaded.\n",
"model_path = config['train']['saved_weights_name']\n",
"\n",
"# We need to create an SSDLoss object in order to pass that to the model loader.\n",
"ssd_loss = SSDLoss(neg_pos_ratio=3, alpha=1.0)\n",
"\n",
"K.clear_session() # Clear previous models from memory.\n",
"\n",
"model = load_model(model_path, custom_objects={'AnchorBoxes': AnchorBoxes,\n",
" 'L2Normalization': L2Normalization,\n",
" 'DecodeDetections': DecodeDetections,\n",
" 'compute_loss': ssd_loss.compute_loss})\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tiempo Total: 0.629\n",
"Tiempo promedio por imagen: 0.035\n",
"OK\n"
]
}
],
"source": [
"image_paths = []\n",
"for inp in input_path:\n",
" if os.path.isdir(inp):\n",
" for inp_file in os.listdir(inp):\n",
" image_paths += [inp + inp_file]\n",
" else:\n",
" image_paths += [inp]\n",
"\n",
"image_paths = [inp_file for inp_file in image_paths if (inp_file[-4:] in ['.jpg', '.png', 'JPEG'])]\n",
"times = []\n",
"\n",
"\n",
"for img_path in image_paths:\n",
" orig_images = [] # Store the images here.\n",
" input_images = [] # Store resized versions of the images here.\n",
" #print(img_path)\n",
"\n",
" # preprocess image for network\n",
" orig_images.append(imread(img_path))\n",
" img = image.load_img(img_path, target_size=(img_height, img_width))\n",
" img = image.img_to_array(img)\n",
" input_images.append(img)\n",
" input_images = np.array(input_images)\n",
" # process image\n",
" start = time.time()\n",
" y_pred = model.predict(input_images)\n",
" y_pred_decoded = decode_detections(y_pred,\n",
" confidence_thresh=score_threshold,\n",
" iou_threshold=score_threshold_iou,\n",
" top_k=200,\n",
" normalize_coords=True,\n",
" img_height=img_height,\n",
" img_width=img_width)\n",
"\n",
"\n",
" #print(\"processing time: \", time.time() - start)\n",
" times.append(time.time() - start)\n",
" # correct for image scale\n",
"\n",
" # visualize detections\n",
" # Set the colors for the bounding boxes\n",
" colors = plt.cm.brg(np.linspace(0, 1, 21)).tolist()\n",
"\n",
" plt.figure(figsize=(20,12))\n",
" plt.imshow(orig_images[0],cmap = 'gray')\n",
"\n",
" current_axis = plt.gca()\n",
" #print(y_pred)\n",
" for box in y_pred_decoded[0]:\n",
" # Transform the predicted bounding boxes for the 300x300 image to the original image dimensions.\n",
"\n",
" xmin = box[2] * orig_images[0].shape[1] / img_width\n",
" ymin = box[3] * orig_images[0].shape[0] / img_height\n",
" xmax = box[4] * orig_images[0].shape[1] / img_width\n",
" ymax = box[5] * orig_images[0].shape[0] / img_height\n",
"\n",
" color = colors[int(box[0])]\n",
" label = '{}: {:.2f}'.format(classes[int(box[0])], box[1])\n",
" current_axis.add_patch(plt.Rectangle((xmin, ymin), xmax-xmin, ymax-ymin, color=color, fill=False, linewidth=2))\n",
" current_axis.text(xmin, ymin, label, size='x-large', color='white', bbox={'facecolor':color, 'alpha':1.0})\n",
"\n",
" #plt.figure(figsize=(15, 15))\n",
" #plt.axis('off')\n",
" save_path = output_path + img_path.split('/')[-1]\n",
" plt.savefig(save_path)\n",
" plt.close()\n",
" \n",
"file = open(output_path + 'time.txt','w')\n",
"\n",
"file.write('Tiempo promedio:' + str(np.mean(times)))\n",
"\n",
"file.close()\n",
"print('Tiempo Total: {:.3f}'.format(np.sum(times)))\n",
"print('Tiempo promedio por imagen: {:.3f}'.format(np.mean(times)))\n",
"print('OK')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"panel : 69\n",
"cell : 423\n"
]
}
],
"source": [
"\n",
"# Summary instance training\n",
"category_train_list = []\n",
"for image_label in train_dataset.labels:\n",
" category_train_list += [i[0] for i in train_dataset.labels[0]]\n",
"summary_category_training = {train_dataset.classes[i]: category_train_list.count(i) for i in list(set(category_train_list))}\n",
"for i in summary_category_training.keys():\n",
" print(i, ': {:.0f}'.format(summary_category_training[i]))\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1 : 6030\n"
]
}
],
"source": [
"for i in summary_category_training.keys():\n",
" print(i, ': {:.0f}'.format(summary_category_training[i]))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"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": "3.6.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in New Issue Copy Permalink