ValueError: Attempted to map inputs that were not found in graph_def: [inputs:0]

[endy-see]

Hi，I download the pretrained model - vgg19_weights_tf_dim_ordering_tf_kernels_notop, when I run python3 train.py ,there occured a bug as follows:
Traceback (most recent call last):
File "train.py", line 87, in
main()
File "train.py", line 31, in main
model = SRNet(shape = cfg.data_shape, name = train_name)
File "/data/zhaoyanmei/projects/SRNet/model.py", line 32, in init
self.build_whole_net_with_loss()
File "/data/zhaoyanmei/projects/SRNet/model.py", line 209, in build_whole_net_with_loss
_ = tf.import_graph_def(vgg_graph_def, input_map = {"inputs:0": i_vgg})
File "/root/miniconda3/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/root/miniconda3/lib/python3.6/site-packages/tensorflow/python/framework/importer.py", line 461, in import_graph_def
', '.join(missing_unused_input_keys))
ValueError: Attempted to map inputs that were not found in graph_def: [inputs:0]

I'm a tensorflow fish bird, is there anyone can help me ?

[lcy0604]

Hello, could you please tell me how to solve this bug?