# 判断是否多GPU载入模型和预训练权重
#----------------------------------------------------#
if ngpus_per_node > 1:
with strategy.scope():
#------------------------------------------------------#
# 创建yolo模型
#------------------------------------------------------#
model_body = yolo_body((None, None, 3), anchors_mask, num_classes, backbone, alpha, weight_decay=weight_decay)
if model_path != '':
#------------------------------------------------------#
# 载入预训练权重
#------------------------------------------------------#
print('Load weights {}.'.format(model_path))
model_body.load_weights(model_path, by_name=True, skip_mismatch=True)
if not eager:
model = get_train_model(model_body, input_shape, num_classes, anchors, anchors_mask, label_smoothing, focal_loss, focal_alpha, focal_gamma)
else:
#------------------------------------------------------#
# 创建yolo模型
#------------------------------------------------------#
model_body = yolo_body((None, None, 3), anchors_mask, num_classes, backbone, alpha, weight_decay=weight_decay)
if model_path != '':
#------------------------------------------------------#
# 载入预训练权重
#------------------------------------------------------#
print('Load weights {}.'.format(model_path))
model_body.load_weights(model_path, by_name=True, skip_mismatch=True)
if not eager:
model = get_train_model(model_body, input_shape, num_classes, anchors, anchors_mask, label_smoothing, focal_loss, focal_alpha, focal_gamma)
#---------------------------#
# 创建yolo模型
#------------------------------------------------------#
model_body = yolo_body((input_shape[0], input_shape[1], 3),
anchors_mask,
num_classes,
phi=phi)
if model_path != '':
#------------------------------------------------------#
# 载入预训练权重
#------------------------------------------------------#
print('Load weights {}.'.format(model_path))
model_body.load_weights(model_path, by_name=True, skip_mismatch=True)
if ngpus_per_node > 1:
model = multi_gpu_model(model_body, gpus=ngpus_per_node)
model = get_train_model(model, input_shape, num_classes, anchors,
anchors_mask, label_smoothing)
else:
model = get_train_model(model_body, input_shape, num_classes, anchors,
anchors_mask, label_smoothing)
#---------------------------#
# 读取数据集对应的txt
#---------------------------#
with open(train_annotation_path, encoding='utf-8') as f:
train_lines = f.readlines()
with open(val_annotation_path, encoding='utf-8') as f:
val_lines = f.readlines()
num_train = len(train_lines)
num_val = len(val_lines)
show_config(