def main(args):
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)
# 300/10 = 30
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:
# convert to a "new" grid size if the image w/h deviates from wanted image size
# 300 / 10 = 10
cell_w = image['width'] / grid_w
cell_h = image['height'] / grid_h
for obj in image['object']:
# ... divided by 10 (a grid size)
# 90 / 10 = 9
relative_w = (float(obj['xmax']) - float(obj['xmin'])) / cell_w
relatice_h = (float(obj["ymax"]) - float(obj['ymin'])) / cell_h
annotation_dims.append(tuple(map(float, (relative_w, relatice_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['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_cell_w = round(config['model']['input_size_w'] / feature_extractor.get_output_shape()[1])
grid_cell_h = round(config['model']['input_size_h'] / feature_extractor.get_output_shape()[0])
image_w = int(config['model']['input_size_w'])
image_h = int(config['model']['input_size_h'])
print("grid cell width:", grid_cell_w)
print("grid cell height:", grid_cell_h)
print("grid size:", feature_extractor.get_output_shape())
for train_img in train_imgs:
image = cv2.imread(train_img["filename"])
image = cv2.resize(image, (image_w, image_h))
for i in range(0, image_w, grid_cell_w):
cv2.line(image, (i, 0), (i, image_h), (0, 0, 255), 2)
for i in range(0, image_h, grid_cell_h):
cv2.line(image, (0, i), (image_w, i), (0, 0, 255), 2)
cv2.imshow("grid viewer", image)
key = cv2.waitKey(0)
if key == ord("q"):
break
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)