def __init__(self, backend,
input_size,
labels,
max_box_per_image,
anchors,
gray_mode = False):
self.input_size = input_size
self.gray_mode = gray_mode
self.labels = list(labels)
self.nb_class = len(self.labels)
self.nb_box = len(anchors)//2
self.class_wt = np.ones(self.nb_class, dtype='float32')
self.anchors = anchors
self.max_box_per_image = max_box_per_image
##########################
# Make the model
##########################
# make the feature extractor layers
if self.gray_mode:
self.input_size = (self.input_size[0], self.input_size[1], 1)
input_image = Input(shape=self.input_size)
else:
self.input_size = (self.input_size[0], self.input_size[1], 3)
input_image = Input(shape=self.input_size)
self.true_boxes = Input(shape=(1, 1, 1, max_box_per_image , 4), name="GT_boxes")
self.feature_extractor = import_feature_extractor(backend, self.input_size)
print(self.feature_extractor.get_output_shape())
self.grid_h, self.grid_w = self.feature_extractor.get_output_shape()
features = self.feature_extractor.extract(input_image)
# make the object detection layer
output = Conv2D(self.nb_box * (4 + 1 + self.nb_class),
(1,1), strides=(1,1),
padding='same',
name='DetectionLayer',
kernel_initializer='he_normal')(features)
output = Reshape((self.grid_h, self.grid_w, self.nb_box, 4 + 1 + self.nb_class), name="YOLO_output")(output)
output = Lambda(lambda args: args[0], name="Insert_GT_Boxes")([output, self.true_boxes])
self.model = Model([input_image, self.true_boxes], output)
self.model.summary()
def main(argv):
config_path = args.conf
num_anchors = args.anchors
with open(config_path) as config_buffer:
config = json.loads(config_buffer.read())
if config['parser_annotation_type'] == 'xml':
# parse annotations of the training set
train_imgs, train_labels = parse_annotation_xml(
config['train']['train_annot_folder'],
config['train']['train_image_folder'], config['model']['labels'])
elif config['parser_annotation_type'] == 'csv':
# parse annotations of the training set
train_imgs, train_labels = parse_annotation_csv(
config['train']['train_csv_file'], config['model']['labels'],
config['train']['train_csv_base_path'])
input_size = (config['model']['input_size_h'],
config['model']['input_size_w'], 3)
feature_extractor = import_feature_extractor(config['model']['backend'],
input_size)
grid_w = config['model'][
'input_size_w'] / feature_extractor.get_output_shape()[1]
grid_h = config['model'][
'input_size_h'] / feature_extractor.get_output_shape()[0]
# run k_mean to find the anchors
annotation_dims = []
for image in train_imgs:
cell_w = image['width'] / grid_w
cell_h = image['height'] / grid_h
for obj in image['object']:
relative_w = (float(obj['xmax']) - float(obj['xmin'])) / cell_w
relative_h = (float(obj["ymax"]) - float(obj['ymin'])) / cell_h
annotation_dims.append(tuple(map(float, (relative_w, relative_h))))
annotation_dims = np.array(annotation_dims)
centroids = run_kmeans(annotation_dims, num_anchors)
# write anchors to file
print('\naverage IOU for', num_anchors, 'anchors:',
'%0.2f' % avg_IOU(annotation_dims, centroids))
print_anchors(centroids)
def _main_(args):
config_path = args.conf
with open(config_path) as config_buffer:
config = json.loads(config_buffer.read())
if config['backup']['create_backup']:
config = create_backup(config)
keras.backend.tensorflow_backend.set_session(get_session())
#path for the training and validation dataset
datasetTrainPath = os.path.join(args.folder, "train")
datasetValPath = os.path.join(args.folder, "val")
for folder in [datasetTrainPath, datasetValPath]:
if not os.path.isdir(folder):
raise Exception("{} doesn't exist!".format(folder))
classesTrain = next(os.walk(datasetTrainPath))[1]
classesVal = next(os.walk(datasetValPath))[1]
if not classesVal == classesTrain:
raise Exception(
"The training and validation classes must be the same!")
else:
folders = classesTrain
#training configuration
epochs = config['train']['nb_epochs']
batchSize = config['train']['batch_size']
width = config['model']['input_size_w']
height = config['model']['input_size_h']
depth = 3 if config['model']['gray_mode'] == False else 1
#config keras generators
if len(
folders
) == 2: #if just have 2 classes, the model will have a binary output
classes = 1
else:
classes = len(folders)
#count all samples
imagesTrainPaths = []
imagesValPaths = []
for folder in folders:
imagesTrainPaths += list(
list_images(os.path.join(datasetTrainPath, folder)))
imagesValPaths += list(
list_images(os.path.join(datasetValPath, folder)))
generator_config = {
'IMAGE_H': height,
'IMAGE_W': width,
'IMAGE_C': depth,
'BATCH_SIZE': batchSize
}
#callbacks
model_name = config['train']['saved_weights_name']
checkPointSaverBest = ModelCheckpoint(model_name,
monitor='val_acc',
verbose=1,
save_best_only=True,
save_weights_only=False,
mode='auto',
period=1)
ckp_model_name = os.path.splitext(model_name)[1] + "_ckp.h5"
checkPointSaver = ModelCheckpoint(ckp_model_name,
verbose=1,
save_best_only=False,
save_weights_only=False,
period=10)
tb = TensorBoard(log_dir=config['train']['tensorboard_log_dir'],
histogram_freq=0,
batch_size=batchSize,
write_graph=True,
write_grads=False,
write_images=False,
embeddings_freq=0,
embeddings_layer_names=None,
embeddings_metadata=None)
#create the classification model
# make the feature extractor layers
if depth == 1:
input_size = (height, width, 1)
input_image = Input(shape=input_size)
else:
input_size = (height, width, 3)
input_image = Input(shape=input_size)
feature_extractor = import_feature_extractor(config['model']['backend'],
input_size)
train_generator = BatchGenerator(imagesTrainPaths,
generator_config,
norm=feature_extractor.normalize,
jitter=True)
val_generator = BatchGenerator(imagesValPaths,
generator_config,
norm=feature_extractor.normalize,
jitter=False)
features = feature_extractor.extract(input_image)
# make the model head
output = Conv2D(classes, (1, 1), padding="same")(features)
output = BatchNormalization()(output)
output = LeakyReLU(alpha=0.1)(output)
output = GlobalAveragePooling2D()(output)
output = Activation("sigmoid")(output) if classes == 1 else Activation(
"softmax")(output)
if config['train']['pretrained_weights'] != "":
model = load_model(config['model']['pretrained_weights'])
else:
model = Model(input_image, output)
opt = Adam()
model.compile(loss="binary_crossentropy"
if classes == 1 else "categorical_crossentropy",
optimizer=opt,
metrics=["accuracy"])
model.summary()
model.fit_generator(train_generator,
steps_per_epoch=len(imagesTrainPaths) // batchSize,
epochs=epochs,
validation_data=val_generator,
validation_steps=len(imagesValPaths) // batchSize,
callbacks=[checkPointSaverBest, checkPointSaver, tb],
workers=12,
max_queue_size=40)