1108 lines
57 KiB
Plaintext
1108 lines
57 KiB
Plaintext
{
|
|
"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}\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",
|
|
"conv1 (Conv2D) (None, 400, 400, 32) 2432 identity_layer[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"bn1 (BatchNormalization) (None, 400, 400, 32) 128 conv1[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"elu1 (ELU) (None, 400, 400, 32) 0 bn1[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"pool1 (MaxPooling2D) (None, 200, 200, 32) 0 elu1[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"conv2 (Conv2D) (None, 200, 200, 48) 13872 pool1[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"bn2 (BatchNormalization) (None, 200, 200, 48) 192 conv2[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"elu2 (ELU) (None, 200, 200, 48) 0 bn2[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"pool2 (MaxPooling2D) (None, 100, 100, 48) 0 elu2[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"conv3 (Conv2D) (None, 100, 100, 64) 27712 pool2[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"bn3 (BatchNormalization) (None, 100, 100, 64) 256 conv3[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"elu3 (ELU) (None, 100, 100, 64) 0 bn3[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"pool3 (MaxPooling2D) (None, 50, 50, 64) 0 elu3[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"conv4 (Conv2D) (None, 50, 50, 64) 36928 pool3[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"bn4 (BatchNormalization) (None, 50, 50, 64) 256 conv4[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"elu4 (ELU) (None, 50, 50, 64) 0 bn4[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"pool4 (MaxPooling2D) (None, 25, 25, 64) 0 elu4[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"conv5 (Conv2D) (None, 25, 25, 48) 27696 pool4[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"bn5 (BatchNormalization) (None, 25, 25, 48) 192 conv5[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"elu5 (ELU) (None, 25, 25, 48) 0 bn5[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"pool5 (MaxPooling2D) (None, 12, 12, 48) 0 elu5[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"conv6 (Conv2D) (None, 12, 12, 48) 20784 pool5[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"bn6 (BatchNormalization) (None, 12, 12, 48) 192 conv6[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"elu6 (ELU) (None, 12, 12, 48) 0 bn6[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"pool6 (MaxPooling2D) (None, 6, 6, 48) 0 elu6[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"conv7 (Conv2D) (None, 6, 6, 32) 13856 pool6[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"bn7 (BatchNormalization) (None, 6, 6, 32) 128 conv7[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"elu7 (ELU) (None, 6, 6, 32) 0 bn7[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"classes4 (Conv2D) (None, 50, 50, 8) 4616 elu4[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"classes5 (Conv2D) (None, 25, 25, 8) 3464 elu5[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"classes6 (Conv2D) (None, 12, 12, 8) 3464 elu6[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"classes7 (Conv2D) (None, 6, 6, 8) 2312 elu7[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"boxes4 (Conv2D) (None, 50, 50, 16) 9232 elu4[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"boxes5 (Conv2D) (None, 25, 25, 16) 6928 elu5[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"boxes6 (Conv2D) (None, 12, 12, 16) 6928 elu6[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"boxes7 (Conv2D) (None, 6, 6, 16) 4624 elu7[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"classes4_reshape (Reshape) (None, 10000, 2) 0 classes4[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"classes5_reshape (Reshape) (None, 2500, 2) 0 classes5[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"classes6_reshape (Reshape) (None, 576, 2) 0 classes6[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"classes7_reshape (Reshape) (None, 144, 2) 0 classes7[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"anchors4 (AnchorBoxes) (None, 50, 50, 4, 8) 0 boxes4[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"anchors5 (AnchorBoxes) (None, 25, 25, 4, 8) 0 boxes5[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"anchors6 (AnchorBoxes) (None, 12, 12, 4, 8) 0 boxes6[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"anchors7 (AnchorBoxes) (None, 6, 6, 4, 8) 0 boxes7[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"classes_concat (Concatenate) (None, 13220, 2) 0 classes4_reshape[0][0] \n",
|
|
" classes5_reshape[0][0] \n",
|
|
" classes6_reshape[0][0] \n",
|
|
" classes7_reshape[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"boxes4_reshape (Reshape) (None, 10000, 4) 0 boxes4[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"boxes5_reshape (Reshape) (None, 2500, 4) 0 boxes5[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"boxes6_reshape (Reshape) (None, 576, 4) 0 boxes6[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"boxes7_reshape (Reshape) (None, 144, 4) 0 boxes7[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"anchors4_reshape (Reshape) (None, 10000, 8) 0 anchors4[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"anchors5_reshape (Reshape) (None, 2500, 8) 0 anchors5[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"anchors6_reshape (Reshape) (None, 576, 8) 0 anchors6[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"anchors7_reshape (Reshape) (None, 144, 8) 0 anchors7[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"classes_softmax (Activation) (None, 13220, 2) 0 classes_concat[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"boxes_concat (Concatenate) (None, 13220, 4) 0 boxes4_reshape[0][0] \n",
|
|
" boxes5_reshape[0][0] \n",
|
|
" boxes6_reshape[0][0] \n",
|
|
" boxes7_reshape[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"anchors_concat (Concatenate) (None, 13220, 8) 0 anchors4_reshape[0][0] \n",
|
|
" anchors5_reshape[0][0] \n",
|
|
" anchors6_reshape[0][0] \n",
|
|
" anchors7_reshape[0][0] \n",
|
|
"__________________________________________________________________________________________________\n",
|
|
"predictions (Concatenate) (None, 13220, 14) 0 classes_softmax[0][0] \n",
|
|
" boxes_concat[0][0] \n",
|
|
" anchors_concat[0][0] \n",
|
|
"==================================================================================================\n",
|
|
"Total params: 186,192\n",
|
|
"Trainable params: 185,520\n",
|
|
"Non-trainable params: 672\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_7_fault_1.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": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Processing image set 'train.txt': 100%|██████████| 33/33 [00:00<00:00, 101.41it/s]\n",
|
|
"Processing image set 'test.txt': 100%|██████████| 2/2 [00:00<00:00, 61.30it/s]\n",
|
|
"1 : 444\n",
|
|
"Number of images in the training dataset:\t 33\n",
|
|
"Number of images in the validation dataset:\t 2\n",
|
|
"WARNING:tensorflow:From /home/dl-desktop/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/tensorflow/python/ops/math_grad.py:102: div (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
|
|
"Instructions for updating:\n",
|
|
"Deprecated in favor of operator or tf.math.divide.\n",
|
|
"Epoch 1/500\n",
|
|
"\n",
|
|
"Epoch 00001: LearningRateScheduler setting learning rate to 0.001.\n",
|
|
"100/100 [==============================] - 25s 246ms/step - loss: 11.5508 - val_loss: 6.3620\n",
|
|
"\n",
|
|
"Epoch 00001: val_loss improved from inf to 6.36203, saving model to experimento_ssd7_fault_1.h5\n",
|
|
"Epoch 2/500\n",
|
|
"\n",
|
|
"Epoch 00002: LearningRateScheduler setting learning rate to 0.001.\n",
|
|
"100/100 [==============================] - 22s 225ms/step - loss: 7.4845 - val_loss: 12.4694\n",
|
|
"\n",
|
|
"Epoch 00002: val_loss did not improve from 6.36203\n",
|
|
"Epoch 3/500\n",
|
|
"\n",
|
|
"Epoch 00003: LearningRateScheduler setting learning rate to 0.001.\n",
|
|
"100/100 [==============================] - 24s 237ms/step - loss: 7.0083 - val_loss: 5.9608\n",
|
|
"\n",
|
|
"Epoch 00003: val_loss improved from 6.36203 to 5.96082, saving model to experimento_ssd7_fault_1.h5\n",
|
|
"Epoch 4/500\n",
|
|
"\n",
|
|
"Epoch 00004: LearningRateScheduler setting learning rate to 0.001.\n",
|
|
"100/100 [==============================] - 23s 232ms/step - loss: 6.3241 - val_loss: 7.0951\n",
|
|
"\n",
|
|
"Epoch 00004: val_loss did not improve from 5.96082\n",
|
|
"Epoch 5/500\n",
|
|
"\n",
|
|
"Epoch 00005: LearningRateScheduler setting learning rate to 0.001.\n",
|
|
"100/100 [==============================] - 24s 239ms/step - loss: 5.9832 - val_loss: 5.5583\n",
|
|
"\n",
|
|
"Epoch 00005: val_loss improved from 5.96082 to 5.55828, saving model to experimento_ssd7_fault_1.h5\n",
|
|
"Epoch 6/500\n",
|
|
"\n",
|
|
"Epoch 00006: LearningRateScheduler setting learning rate to 0.001.\n",
|
|
"100/100 [==============================] - 25s 248ms/step - loss: 6.0359 - val_loss: 10.5573\n",
|
|
"\n",
|
|
"Epoch 00006: val_loss did not improve from 5.55828\n",
|
|
"Epoch 7/500\n",
|
|
"\n",
|
|
"Epoch 00007: LearningRateScheduler setting learning rate to 0.001.\n",
|
|
"100/100 [==============================] - 23s 232ms/step - loss: 5.9338 - val_loss: 12.5439\n",
|
|
"\n",
|
|
"Epoch 00007: val_loss did not improve from 5.55828\n",
|
|
"Epoch 8/500\n",
|
|
"\n",
|
|
"Epoch 00008: LearningRateScheduler setting learning rate to 0.001.\n",
|
|
"100/100 [==============================] - 23s 228ms/step - loss: 6.3084 - val_loss: 8.1511\n",
|
|
"\n",
|
|
"Epoch 00008: val_loss did not improve from 5.55828\n",
|
|
"Epoch 9/500\n",
|
|
"\n",
|
|
"Epoch 00009: LearningRateScheduler setting learning rate to 0.001.\n",
|
|
"100/100 [==============================] - 22s 222ms/step - loss: 5.8168 - val_loss: 10.5703\n",
|
|
"\n",
|
|
"Epoch 00009: val_loss did not improve from 5.55828\n",
|
|
"Epoch 10/500\n",
|
|
"\n",
|
|
"Epoch 00010: LearningRateScheduler setting learning rate to 0.001.\n",
|
|
"100/100 [==============================] - 23s 235ms/step - loss: 5.4740 - val_loss: 5.8349\n",
|
|
"\n",
|
|
"Epoch 00010: val_loss did not improve from 5.55828\n",
|
|
"Epoch 11/500\n",
|
|
"\n",
|
|
"Epoch 00011: LearningRateScheduler setting learning rate to 0.001.\n",
|
|
"100/100 [==============================] - 23s 227ms/step - loss: 5.4750 - val_loss: 4.4782\n",
|
|
"\n",
|
|
"Epoch 00011: val_loss improved from 5.55828 to 4.47816, saving model to experimento_ssd7_fault_1.h5\n",
|
|
"Epoch 12/500\n",
|
|
"\n",
|
|
"Epoch 00012: LearningRateScheduler setting learning rate to 0.001.\n",
|
|
" 88/100 [=========================>....] - ETA: 2s - loss: 5.5271"
|
|
]
|
|
}
|
|
],
|
|
"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 = 500 #config['train']['nb_epochs']\n",
|
|
"steps_per_epoch = 100\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": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"classes"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"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": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"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": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"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": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"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_1/']\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 = 0.25\n",
|
|
"score_threshold_iou = 0.5\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": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"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": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"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": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"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
|
|
}
|