Closed thisisandreeeee closed 7 years ago
Same error. It is related to python2 and 3 differences. I solved it by changing the corresponding 2 lines in _shortcut into:
stride_width = input._keras_shape[2] // residual._keras_shape[2]
stride_height = input._keras_shape[3] // residual._keras_shape[3]
Thanks. Fixed.
I've been trying to use resnet for an image classification task, and am encountering the following assertion error:
I've changed the input shape and output dimension of the resnet() function, and left the other helper functions untouched, and the way I am using resnet() is as follows:
The error is being thrown at the model.fit_generator line, and it might be useful to note that I've tested the same code on much simpler conv nets.
Any thoughts on how I may proceed dealing with this error?