# 使用restnet网络
# check if weight path was passed via command line
if cfg.input_weight_path: # 这里已经被赋值为cfg里的值
cfg.base_net_weights = cfg.input_weight_path
else:
# set the path to weights based on backend and model
cfg.base_net_weights = nn.get_weight_path()
# 设定restore路径
all_imgs, classes_count, class_mapping, bird_class_count, bird_class_mapping = get_data(
cfg.train_path) # get_data函数在pascalvocparser.py里变
data_lei = march.get_voc_label(all_imgs,
classes_count,
class_mapping,
bird_class_count,
bird_class_mapping,
trainable=True)
if 'bg' not in classes_count:
classes_count['bg'] = 0
class_mapping['bg'] = len(class_mapping)
cfg.class_mapping = class_mapping
inv_map = {v: k for k, v in class_mapping.items()}
print('Training images per class:')
pprint.pprint(classes_count)
print('Num classes (including bg) = {}'.format(len(classes_count)))
print('Training bird per class:')
else:
print('Not a valid model')
raise ValueError
if cfg.input_weight_path: # 这里已经被赋值为cfg里的值
cfg.base_net_weights = cfg.input_weight_path
else:
print('does not init')
#raise ValueError
all_imgs, classes_count, bird_class_count = get_data(cfg.train_path,
part_class_mapping)
data_lei = march.get_voc_label(all_imgs,
classes_count,
part_class_mapping,
bird_class_count,
bird_class_mapping,
config=cfg,
trainable=False)
#pprint.pprint(classes_count)
#pprint.pprint(part_class_mapping)
# 这里的类在match里边定义
if 'bg' not in classes_count:
classes_count['bg'] = 0
part_class_mapping['bg'] = len(part_class_mapping)
cfg.class_mapping = part_class_mapping
print('Training images per class:')
pprint.pprint(classes_count)
pprint.pprint(part_class_mapping)