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())
###############################
# Parse the annotations
###############################
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'])
# parse annotations of the validation set, if any, otherwise split the training set
if os.path.exists(config['valid']['valid_annot_folder']):
valid_imgs, valid_labels = parse_annotation_xml(
config['valid']['valid_annot_folder'],
config['valid']['valid_image_folder'],
config['model']['labels'])
split = False
else:
split = True
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'])
# parse annotations of the validation set, if any, otherwise split the training set
if os.path.exists(config['valid']['valid_csv_file']):
valid_imgs, valid_labels = parse_annotation_csv(
config['valid']['valid_csv_file'], config['model']['labels'],
config['valid']['valid_csv_base_path'])
split = False
else:
split = True
else:
raise ValueError(
"'parser_annotations_type' must be 'xml' or 'csv' not {}.".format(
config['parser_annotations_type']))
if split:
train_valid_split = int(0.8 * len(train_imgs))
np.random.shuffle(train_imgs)
valid_imgs = train_imgs[train_valid_split:]
train_imgs = train_imgs[:train_valid_split]
if len(config['model']['labels']) > 0:
overlap_labels = set(config['model']['labels']).intersection(
set(train_labels.keys()))
print('Seen labels:\t', train_labels)
print('Given labels:\t', config['model']['labels'])
print('Overlap labels:\t', overlap_labels)
if len(overlap_labels) < len(config['model']['labels']):
print(
'Some labels have no annotations! Please revise the list of labels in the config.json file!'
)
return
else:
print('No labels are provided. Saving on all seen labels.')
config['model']['labels'] = train_labels.keys()
with open("labels.json", 'w') as outfile:
json.dump({"labels": list(train_labels.keys())}, outfile)
if os.path.isdir("./roi_dataset"):
print("roi_dataset already exists, please move or delete it first.")
return
else:
os.mkdir("roi_dataset")
os.mkdir("roi_dataset/train")
os.mkdir("roi_dataset/val")
all_imgs = [train_imgs, valid_imgs]
for j, folder_name in enumerate(["train", "val"]):
print("generating", folder_name)
for img in tqdm(all_imgs[j]):
image = cv2.imread(img['filename'])
for i, obj in enumerate(img['object']):
xmin = obj['xmin']
ymin = obj['ymin']
xmax = obj['xmax']
ymax = obj['ymax']
name = obj['name']
if not os.path.isdir("roi_dataset/{}/{}".format(
folder_name, name)):
os.mkdir("roi_dataset/{}/{}".format(folder_name, name))
roi = image[ymin:ymax, xmin:xmax]
base_name = os.path.basename(img['filename'])
base_name, ext = os.path.splitext(base_name)
cv2.imwrite(
"roi_dataset/{}/{}/{}_{}_{}.jpg".format(
folder_name, name, name, base_name, i), roi)
def _main_(args):
config_path = args.conf
keras.backend.tensorflow_backend.set_session(get_session())
with open(config_path) as config_buffer:
config = json.loads(config_buffer.read())
if config['backup']['create_backup']:
config = create_backup(config)
###############################
# Parse the annotations
###############################
if config['parser_annotation_type'] == 'xml':
# parse annotations of the training set
train_imgs, train_labels = parse_annotation(
config['train']['train_annot_folder'],
config['train']['train_image_folder'], config['model']['labels'])
# parse annotations of the validation set, if any, otherwise split the training set
if os.path.exists(config['valid']['valid_annot_folder']):
valid_imgs, valid_labels = parse_annotation(
config['valid']['valid_annot_folder'],
config['valid']['valid_image_folder'],
config['model']['labels'])
split = False
else:
split = True
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'])
# parse annotations of the validation set, if any, otherwise split the training set
if os.path.exists(config['valid']['valid_csv_file']):
valid_imgs, valid_labels = parse_annotation_csv(
config['valid']['valid_csv_file'], config['model']['labels'],
config['valid']['valid_csv_base_path'])
split = False
else:
print("Validation file not found commensing split")
split = True
else:
raise ValueError(
"'parser_annotations_type' must be 'xml' or 'csv' not {}.".format(
config['parser_annotations_type']))
if split:
train_valid_split = int(0.8 * len(train_imgs))
np.random.shuffle(train_imgs)
valid_imgs = train_imgs[train_valid_split:]
train_imgs = train_imgs[:train_valid_split]
if len(config['model']['labels']) > 0:
overlap_labels = set(config['model']['labels']).intersection(
set(train_labels.keys()))
print('Seen labels:\t', train_labels)
print('Given labels:\t', config['model']['labels'])
print('Overlap labels:\t', overlap_labels)
if len(overlap_labels) < len(config['model']['labels']):
print(
'Some labels have no annotations! Please revise the list of labels in the config.json file!'
)
return
else:
print('No labels are provided. Train on all seen labels.')
config['model']['labels'] = train_labels.keys()
with open("labels.json", 'w') as outfile:
json.dump({"labels": list(train_labels.keys())}, outfile)
###############################
# Construct the model
###############################
yolo = YOLO(backend=config['model']['backend'],
input_size=(config['model']['input_size_h'],
config['model']['input_size_w']),
labels=config['model']['labels'],
max_box_per_image=config['model']['max_box_per_image'],
anchors=config['model']['anchors'],
gray_mode=config['model']['gray_mode'])
###############################
# Load the pretrained weights (if any)
###############################
if os.path.exists(config['train']['pretrained_weights']):
print("Loading pre-trained weights in",
config['train']['pretrained_weights'])
yolo.load_weights(config['train']['pretrained_weights'])
###############################
# Start the training process
###############################
yolo.train(train_imgs=train_imgs,
valid_imgs=valid_imgs,
train_times=config['train']['train_times'],
valid_times=config['valid']['valid_times'],
nb_epochs=config['train']['nb_epochs'],
learning_rate=config['train']['learning_rate'],
batch_size=config['train']['batch_size'],
warmup_epochs=config['train']['warmup_epochs'],
object_scale=config['train']['object_scale'],
no_object_scale=config['train']['no_object_scale'],
coord_scale=config['train']['coord_scale'],
class_scale=config['train']['class_scale'],
saved_weights_name=config['train']['saved_weights_name'],
debug=config['train']['debug'],
early_stop=config['train']['early_stop'],
workers=config['train']['workers'],
max_queue_size=config['train']['max_queue_size'],
tb_logdir=config['train']['tensorboard_log_dir'])
def _main_(args):
config_path = args.conf
weights_path = args.weights
keras.backend.tensorflow_backend.set_session(get_session())
with open(config_path) as config_buffer:
config = json.loads(config_buffer.read())
if weights_path == '':
weights_path = config['train']['pretrained_weights"']
###############################
# Parse the annotations
###############################
without_valid_imgs = False
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'])
# parse annotations of the validation set, if any.
if os.path.exists(config['valid']['valid_annot_folder']):
valid_imgs, valid_labels = parse_annotation_xml(
config['valid']['valid_annot_folder'],
config['valid']['valid_image_folder'],
config['model']['labels'])
else:
without_valid_imgs = True
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'])
# parse annotations of the validation set, if any.
if os.path.exists(config['valid']['valid_csv_file']):
valid_imgs, valid_labels = parse_annotation_csv(
config['valid']['valid_csv_file'], config['model']['labels'],
config['valid']['valid_csv_base_path'])
else:
without_valid_imgs = True
else:
raise ValueError(
"'parser_annotations_type' must be 'xml' or 'csv' not {}.".format(
config['parser_annotations_type']))
#remove samples without objects in the image
for i in range(len(train_imgs) - 1, 0, -1):
if len(train_imgs[i]['object']) == 0:
del train_imgs[i]
if len(config['model']['labels']) > 0:
overlap_labels = set(config['model']['labels']).intersection(
set(train_labels.keys()))
print('Seen labels:\t', train_labels)
print('Given labels:\t', config['model']['labels'])
print('Overlap labels:\t', overlap_labels)
if len(overlap_labels) < len(config['model']['labels']):
print(
'Some labels have no annotations! Please revise the list of labels in the config.json file!'
)
return
else:
print('No labels are provided. Evaluate on all seen labels.')
config['model']['labels'] = train_labels.keys()
with open("labels.json", 'w') as outfile:
json.dump({"labels": list(train_labels.keys())}, outfile)
###############################
# Construct the model
###############################
yolo = YOLO(backend=config['model']['backend'],
input_size=(config['model']['input_size_h'],
config['model']['input_size_w']),
labels=config['model']['labels'],
max_box_per_image=config['model']['max_box_per_image'],
anchors=config['model']['anchors'],
gray_mode=config['model']['gray_mode'])
###############################
# Load the pretrained weights (if any)
###############################
if weights_path != '':
print("Loading pre-trained weights in", weights_path)
yolo.load_weights(weights_path)
elif os.path.exists(config['train']['pretrained_weights']):
print("Loading pre-trained weights in",
config['train']['pretrained_weights'])
yolo.load_weights(config['train']['pretrained_weights'])
else:
raise Exception("No pretrained weights found.")
###############################
# Evaluate the network
###############################
print("calculing mAP for iou threshold = {}".format(args.iou))
generator_config = {
'IMAGE_H': yolo.input_size[0],
'IMAGE_W': yolo.input_size[1],
'IMAGE_C': yolo.input_size[2],
'GRID_H': yolo.grid_h,
'GRID_W': yolo.grid_w,
'BOX': yolo.nb_box,
'LABELS': yolo.labels,
'CLASS': len(yolo.labels),
'ANCHORS': yolo.anchors,
'BATCH_SIZE': 4,
'TRUE_BOX_BUFFER': yolo.max_box_per_image,
}
if not without_valid_imgs:
valid_generator = BatchGenerator(valid_imgs,
generator_config,
norm=yolo.feature_extractor.normalize,
jitter=False)
valid_eval = YOLO.MAP_evaluation(yolo,
valid_generator,
iou_threshold=args.iou)
mAP, average_precisions = valid_eval.evaluate_mAP()
for label, average_precision in average_precisions.items():
print(yolo.labels[label], '{:.4f}'.format(average_precision))
print('validation dataset mAP: {:.4f}\n'.format(mAP))
train_generator = BatchGenerator(train_imgs,
generator_config,
norm=yolo.feature_extractor.normalize,
jitter=False)
train_eval = YOLO.MAP_evaluation(yolo,
train_generator,
iou_threshold=args.iou)
mAP, average_precisions = train_eval.evaluate_mAP()
for label, average_precision in average_precisions.items():
print(yolo.labels[label], '{:.4f}'.format(average_precision))
print('training dataset mAP: {:.4f}'.format(mAP))