loading weights error in the testing step, after a successful transfer learning training

[0xzhou]

Hi, Thank you very much for the nice code and instructions.
I use your ResNet18 model as an image encoder in training a VAE. I can train with your ResNet18 model with the pretrained weights. But when I want to test the trained model by loading the saved weights, I got the following errors. Could you please give me some advice on fixing it?

Traceback (most recent call last): File "test_MMI.py", line 123, in <module> main(arg_parser.parse_test_arguments(sys.argv[1:])) File "test_MMI.py", line 62, in main model.load_weights(weights_path) File "/home/zmy/anaconda3/envs/tfk-3dvae/lib/python3.6/site-packages/tensorflow/python/keras/engine/network.py", line 1516, in load_weights saving.load_weights_from_hdf5_group(f, self.layers) File "/home/zmy/anaconda3/envs/tfk-3dvae/lib/python3.6/site-packages/tensorflow/python/keras/engine/saving.py", line 810, in load_weights_from_hdf5_group layer, weight_values, original_keras_version, original_backend) File "/home/zmy/anaconda3/envs/tfk-3dvae/lib/python3.6/site-packages/tensorflow/python/keras/engine/saving.py", line 468, in preprocess_weights_for_loading weights = convert_nested_model(weights) File "/home/zmy/anaconda3/envs/tfk-3dvae/lib/python3.6/site-packages/tensorflow/python/keras/engine/saving.py", line 444, in convert_nested_model original_backend=original_backend)) File "/home/zmy/anaconda3/envs/tfk-3dvae/lib/python3.6/site-packages/tensorflow/python/keras/engine/saving.py", line 468, in preprocess_weights_for_loading weights = convert_nested_model(weights) File "/home/zmy/anaconda3/envs/tfk-3dvae/lib/python3.6/site-packages/tensorflow/python/keras/engine/saving.py", line 456, in convert_nested_model original_backend=original_backend)) File "/home/zmy/anaconda3/envs/tfk-3dvae/lib/python3.6/site-packages/tensorflow/python/keras/engine/saving.py", line 468, in preprocess_weights_for_loading weights = convert_nested_model(weights) File "/home/zmy/anaconda3/envs/tfk-3dvae/lib/python3.6/site-packages/tensorflow/python/keras/engine/saving.py", line 444, in convert_nested_model original_backend=original_backend)) File "/home/zmy/anaconda3/envs/tfk-3dvae/lib/python3.6/site-packages/tensorflow/python/keras/engine/saving.py", line 549, in preprocess_weights_for_loading if K.int_shape(layer.weights[0]) != weights[0].shape: IndexError: list index out of range