Visualizing_Understanding_CNN_Implementation

Visualizing_Understanding_CNN_Implementation copied to clipboard


cdata123

When I run your code with keras 2.0.8 tensorflow 1.4.1, I get some problem: tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimension 0 in both shapes must be equal, but are 3 and 384 for 'Assign_6'...

Mr-S-Wang

Why the net can't predict correctly?

1

When i run alexnet.py, the input is an image of 'elephant', the output is 'cockroach', the "imagenet_class_index.json" is ILSVRC2012?

ywh4258222

Transposed filters

1

I was wondering if the deconv filters are trainable, or they are just transpose of the (pretrained) conv filters? If the latter, are we assuming the filters are unitary?

zechenghe

Is there a bug？

2

deconvolution.py about Line 164 # Set other layers to zero new_array = np.zeros_like(self.array) new_array[0, self.f - 1] = self.array[0, self.f - 1] # Set other activations in same layer to...

ywh4258222

When I ran the 'activations.py', I met an error

2

Could you please help me solve it?

tianyu0523