I tried to test the notebook to reproduce the results on MNIST but I have a problem with Tensorflow version 1.15 and the keras2_mnist_cnn_allconv.h5 file. It seems that the latter is a text file and therefore it is not decodable.
/tensorflow-1.15.2/python3.7/keras/engine/saving.py in _deserialize_model(h5dict, custom_objects, compile)
271 if model_config is None:
272 raise ValueError('No model found in config.')
--> 273 model_config = json.loads(model_config.decode('utf-8'))
274 model = model_from_config(model_config, custom_objects=custom_objects)
275 model_weights_group = h5dict['model_weights']
AttributeError: 'str' object has no attribute 'decode'
Here is my attempt on a google colab.
I tried to test the notebook to reproduce the results on MNIST but I have a problem with Tensorflow version 1.15 and the
keras2_mnist_cnn_allconv.h5file. It seems that the latter is a text file and therefore it is not decodable./tensorflow-1.15.2/python3.7/keras/engine/saving.py in _deserialize_model(h5dict, custom_objects, compile)
271 if model_config is None:
272 raise ValueError('No model found in config.')
--> 273 model_config = json.loads(model_config.decode('utf-8'))
274 model = model_from_config(model_config, custom_objects=custom_objects)
275 model_weights_group = h5dict['model_weights']
AttributeError: 'str' object has no attribute 'decode'
Here is my attempt on a google colab.