Created by: luweishuang

for leak of enough training data, I want to only finetune last fc layer params and other layers keep fixed by pretrained model. I do this by setting some layers in network.py, like this

     param_attr = paddle.attr.ParameterAttribute(is_static=True)

def conv_bn_layer(input, filter_size, num_channels_in, num_channels_out, stride,
                  padding, act, index_range_data):
   conv_layer = paddle.layer.img_conv(
        input=input,
        filter_size=filter_size,
        num_channels=num_channels_in,
        num_filters=num_channels_out,
        stride=stride,
        padding=padding,
        act=paddle.activation.Linear(),
        bias_attr=False,
        param_attr=param_attr)
    batch_norm = paddle.layer.batch_norm(input=conv_layer, act=act)
    # reset padding part to 0
    scale_sub_region = paddle.layer.scale_sub_region(batch_norm, index_range_data, value=0.0)
    return scale_sub_region

but when I run "sh run_train.sh"， I get the error remove the is_static, the code will run successfully