CorrMM images and kernel must have the same stack size

[seaofglass]

I don't know what kind of error is this?

I upgraded keras below address.
https://github.com/jayanthkoushik/keras.git.

And also patched a code like this :
out = Conv2D(nb_filter, filter_length, filter_length, subsample=(subsample, subsample), border_mode="valid",dim_ordering='th')(out)

and then edited ~/.keras/keras.json file.

"dim_ordering": "th"

python fast_neural_style.py eval --content-image tubingen.jpg --output-image out.jpg --model test.h5

Using Theano backend.
Traceback (most recent call last):
File "/Users/seaofglass/anaconda/lib/python3.6/site-packages/theano/compile/function_module.py", line 903, in call
self.fn() if output_subset is None else
ValueError: CorrMM images and kernel must have the same stack size

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "fast_neural_style.py", line 168, in
output_image = get_Xtr()
File "/Users/seaofglass/anaconda/lib/python3.6/site-packages/theano/compile/function_module.py", line 917, in call
storage_map=getattr(self.fn, 'storage_map', None))
File "/Users/seaofglass/anaconda/lib/python3.6/site-packages/theano/gof/link.py", line 325, in raise_with_op
reraise(exc_type, exc_value, exc_trace)
File "/Users/seaofglass/anaconda/lib/python3.6/site-packages/six.py", line 692, in reraise
raise value.with_traceback(tb)
File "/Users/seaofglass/anaconda/lib/python3.6/site-packages/theano/compile/function_module.py", line 903, in call
self.fn() if output_subset is None else
ValueError: CorrMM images and kernel must have the same stack size

Apply node that caused the error: CorrMM{valid, (1, 1), (1, 1), 1 False}(IncSubtensor{InplaceSet;::, ::, int64::, int64::}.0, Subtensor{::, ::, ::int64, ::int64}.0)
Toposort index: 479
Inputs types: [TensorType(float32, 4D), TensorType(float32, 4D)]
Inputs shapes: [(1, 256, 386, 258), (64, 128, 3, 3)]
Inputs strides: [(101978112, 398352, 1032, 4), (4608, 36, -12, -4)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Elemwise{add,no_inplace}(CorrMM{valid, (1, 1), (1, 1), 1 False}.0, InplaceDimShuffle{x,0,x,x}.0)]]

Backtrace when the node is created(use Theano flag traceback.limit=N to make it longer):
File "fast_neural_style.py", line 56, in
transformer_net = get_transformer_net(X, weights)
File "/Users/seaofglass/neoart/app/neuralstyle/transformer_net.py", line 88, in get_transformer_net
y = conv_layer(y, 64, 3, upsample=2)
File "/Users/seaofglass/neoart/app/neuralstyle/transformer_net.py", line 65, in conv_layer
out = Conv2D(nb_filter, filter_length, filter_length, subsample=(subsample, subsample), border_mode="valid", dim_ordering='th')(out)
File "/Users/seaofglass/anaconda/lib/python3.6/site-packages/keras/engine/topology.py", line 569, in call
self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
File "/Users/seaofglass/anaconda/lib/python3.6/site-packages/keras/engine/topology.py", line 632, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/Users/seaofglass/anaconda/lib/python3.6/site-packages/keras/engine/topology.py", line 164, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
File "/Users/seaofglass/anaconda/lib/python3.6/site-packages/keras/layers/convolutional.py", line 442, in call
filter_shape=self.W_shape)
File "/Users/seaofglass/anaconda/lib/python3.6/site-packages/keras/backend/theano_backend.py", line 1488, in conv2d
filter_shape=filter_shape)

HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.