2020-01-16 10:51:32 -03:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Detector de Celulas"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"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",
2020-02-19 14:26:55 -03:00
"execution_count": 7,
2020-01-16 10:51:32 -03:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
2020-02-19 14:26:55 -03:00
"Training on: \t{'1': 1}\n",
"\n",
"OK create model\n",
"\n",
"Loading pretrained weights VGG.\n",
"\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, 8) 36872 conv4_3_norm[0][0] \n",
"__________________________________________________________________________________________________\n",
"fc7_mbox_conf (Conv2D) (None, 25, 25, 12) 110604 fc7[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv6_2_mbox_conf (Conv2D) (None, 13, 13, 12) 55308 conv6_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv7_2_mbox_conf (Conv2D) (None, 7, 7, 12) 27660 conv7_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv8_2_mbox_conf (Conv2D) (None, 5, 5, 8) 18440 conv8_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv9_2_mbox_conf (Conv2D) (None, 3, 3, 8) 18440 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, 2) 0 conv4_3_norm_mbox_conf[0][0] \n",
"__________________________________________________________________________________________________\n",
"fc7_mbox_conf_reshape (Reshape) (None, 3750, 2) 0 fc7_mbox_conf[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv6_2_mbox_conf_reshape (Resh (None, 1014, 2) 0 conv6_2_mbox_conf[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv7_2_mbox_conf_reshape (Resh (None, 294, 2) 0 conv7_2_mbox_conf[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv8_2_mbox_conf_reshape (Resh (None, 100, 2) 0 conv8_2_mbox_conf[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv9_2_mbox_conf_reshape (Resh (None, 36, 2) 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, 2) 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, 2) 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, 14) 0 mbox_conf_softmax[0][0] \n",
" mbox_loc[0][0] \n",
" mbox_priorbox[0][0] \n",
"==================================================================================================\n",
"Total params: 23,745,908\n",
"Trainable params: 23,745,908\n",
"Non-trainable params: 0\n",
"__________________________________________________________________________________________________\n"
2020-01-16 10:51:32 -03:00
]
}
],
"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",
2020-02-06 16:47:03 -03:00
"sys.path += [os.path.abspath('ssd_keras-master')]\n",
2020-01-16 10:51:32 -03:00
"\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",
2020-02-19 14:26:55 -03:00
"config_path = 'config_300_fault_1.json'\n",
2020-01-16 10:51:32 -03:00
"\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 = [0.1, 0.2, 0.37, 0.54, 0.71, 0.88, 1.05] # 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",
2020-02-19 14:26:55 -03:00
" from models.keras_ssd300 import ssd_300\n",
2020-01-16 10:51:32 -03:00
"\n",
" model = ssd_300(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",
2020-02-19 14:26:55 -03:00
"execution_count": 5,
2020-01-16 10:51:32 -03:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
2020-02-19 14:26:55 -03:00
"Processing image set 'train.txt': 100%|██████████| 1/1 [00:00<00:00, 18.73it/s]\n",
"Processing image set 'test.txt': 100%|██████████| 1/1 [00:00<00:00, 20.23it/s]\n",
2020-01-16 10:51:32 -03:00
"panel : 69\n",
"Number of images in the training dataset:\t 1\n",
"Number of images in the validation dataset:\t 1\n",
"Epoch 1/100\n",
"\n",
"Epoch 00001: LearningRateScheduler setting learning rate to 0.001.\n",
2020-02-19 14:26:55 -03:00
"27/50 [===============>..............] - ETA: 19s - loss: 10.4861"
2020-01-16 10:51:32 -03:00
]
},
{
2020-02-19 14:26:55 -03:00
"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-5-eddb2cf7cd19>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 201\u001b[0m \u001b[0mvalidation_steps\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mceil\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mval_dataset_size\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[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 202\u001b[0m \u001b[0minitial_epoch\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minitial_epoch\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 203\u001b[0;31m verbose = 1 if config['train']['debug'] else 2)\n\u001b[0m\u001b[1;32m 204\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 205\u001b[0m \u001b[0mhistory_path\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mconfig\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'train'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'saved_weights_name'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[0;34m(\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[0;34m'_history'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/envs/model/lib/python3.6/site-packages/keras/legacy/interfaces.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 89\u001b[0m warnings.warn('Update your `' + object_name + '` call to the ' +\n\u001b[1;32m 90\u001b[0m 'Keras 2 API: ' + signature, stacklevel=2)\n\u001b[0;32m---> 91\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\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 92\u001b[0m \u001b[0mwrapper\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_original_function\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 93\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mwrapper\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/envs/model/lib/python3.6/site-packages/keras/engine/training.py\u001b[0m in \u001b[0;36mfit_generator\u001b[0;34m(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)\u001b[0m\n\u001b[1;32m 1416\u001b[0m \u001b[0muse_multiprocessing\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0muse_multiprocessing\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1417\u001b[0m \u001b[0mshuffle\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mshuffle\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1418\u001b[0;31m initial_epoch=initial_epoch)\n\u001b[0m\u001b[1;32m 1419\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1420\u001b[0m \u001b[0;34m@\u001b[0m\u001b[0minterfaces\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlegacy_generator_methods_support\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/envs/model/lib/python3.6/site-packages/keras/engine/training_generator.py\u001b[0m in \u001b[0;36mfit_generator\u001b[0;34m(model, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)\u001b[0m\n\u001b[1;32m 215\u001b[0m outs = model.train_on_batch(x, y,\n\u001b[1;32m 216\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msample_weight\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 217\u001b[0;31m class_weight=class_weight)\n\u001b[0m\u001b[1;32m 218\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 219\u001b[0m \u001b[0mouts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mto_list\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mouts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/envs/model/lib/python3.6/site-packages/keras/engine/training.py\u001b[0m in \u001b[0;36mtrain_on_batch\u001b[0;34m(self, x, y, sample_weight, class_weight)\u001b[0m\n\u001b[1;32m 1215\u001b[0m \u001b[0mins\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mx\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0my\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0msample_weights\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1216\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_make_train_function\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[0;32m-> 1217\u001b[0;31m \u001b[0moutputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mins\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 1218\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0munpack_singleton\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1219\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/envs/model/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m 2713\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_legacy_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2714\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2715\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\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 2716\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 2717\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mpy_any\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mis_tensor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mx\u001b[0m \u001b[0;32min\u001b[0m \u001b[0minputs\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[0;32m~/anaconda3/envs/model/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m 2673\u001b[0m \u001b[0mfetched\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_callable_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0marray_vals\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_metadata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2674\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[0;32m-> 2675\u001b[0;31m \u001b[0mfetched\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_callable_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0marray_vals\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 2676\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mfetched\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutputs\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 2677\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/envs/model/lib/python3.6/site-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1380\u001b[0m ret = tf_session.TF_SessionRunCallable(\n\u001b[1;32m 1381\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_session\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_handle\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstatus\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1382\u001b[0;31m run_metadata_ptr)\n\u001b[0m\u001b[1;32m 1383\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1384\u001b[0m \u001b[0mproto_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTF_GetBuffer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrun_metadata_ptr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
2020-01-16 10:51:32 -03:00
]
}
],
"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 = ['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",
"# 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 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",
"\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 = 50\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),\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": []
},
{
"cell_type": "code",
"execution_count": 15,
"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_ssd7_panel_cell.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.show()\n",
"\n",
"print(config['train']['saved_weights_name'])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Evaluación del Modelo"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing image set 'train.txt': 100%|██████████| 1/1 [00:00<00:00, 20.74it/s]\n",
"Processing image set 'test.txt': 100%|██████████| 1/1 [00:00<00:00, 25.40it/s]\n",
"Number of images in the evaluation dataset: 1\n",
"\n",
"Producing predictions batch-wise: 100%|██████████| 1/1 [00:00<00:00, 1.50it/s]\n",
"Matching predictions to ground truth, class 1/1.: 100%|██████████| 200/200 [00:00<00:00, 7283.80it/s]\n",
"Computing precisions and recalls, class 1/1\n",
"Computing average precision, class 1/1\n",
"200 instances of class panel with average precision: 0.8982\n",
"mAP using the weighted average of precisions among classes: 0.8982\n",
"mAP: 0.8982\n",
"panel AP 0.898\n",
"\n",
" mAP 0.898\n"
]
}
],
"source": [
"\n",
"config_path = 'config_7_panel.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": "markdown",
"metadata": {},
"source": [
"Cargar nuevamente el modelo desde los pesos.\n",
"Predicción"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Training on: \t{'panel': 1}\n",
"\n"
]
}
],
"source": [
"from imageio import imread\n",
"from keras.preprocessing import image\n",
"import time\n",
"\n",
"config_path = 'config_7_panel.json'\n",
"input_path = ['panel_jpg/Mision_1/', 'panel_jpg/Mision_2/']\n",
"output_path = 'result_ssd7_panel_cell/'\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 = 0.8\n",
"score_threshold_iou = 0.3\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": [
"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": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"__________________________________________________________________________________________________\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, 12) 6924 elu4[0][0] \n",
"__________________________________________________________________________________________________\n",
"classes5 (Conv2D) (None, 25, 25, 12) 5196 elu5[0][0] \n",
"__________________________________________________________________________________________________\n",
"classes6 (Conv2D) (None, 12, 12, 12) 5196 elu6[0][0] \n",
"__________________________________________________________________________________________________\n",
"classes7 (Conv2D) (None, 6, 6, 12) 3468 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, 3) 0 classes4[0][0] \n",
"__________________________________________________________________________________________________\n",
"classes5_reshape (Reshape) (None, 2500, 3) 0 classes5[0][0] \n",
"__________________________________________________________________________________________________\n",
"classes6_reshape (Reshape) (None, 576, 3) 0 classes6[0][0] \n",
"__________________________________________________________________________________________________\n",
"classes7_reshape (Reshape) (None, 144, 3) 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, 3) 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, 3) 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, 15) 0 classes_softmax[0][0] \n",
" boxes_concat[0][0] \n",
" anchors_concat[0][0] \n",
"==================================================================================================\n",
"Total params: 193,120\n",
"Trainable params: 192,448\n",
"Non-trainable params: 672\n",
"__________________________________________________________________________________________________\n"
]
}
],
"source": [
"\n",
"\n",
"\n",
"model.summary()"
]
},
{
"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
}
