I met this error about CorrMM images and kernel must have the same stack size

[hhya1013]

Thanks for you code,whenI run it,i met this error, I hope you can help me solve this problem.
Traceback (most recent call last):
File "main.py", line 114, in
predictions = m.predict_generator(generator_test(b_s=b_s, imgs_test_path=imgs_test_path), nb_imgs_test)[0]
File "/home/han/.local/lib/python2.7/site-packages/keras/engine/training.py", line 1634, in predict_generator
outs = self.predict_on_batch(x)
File "/home/han/.local/lib/python2.7/site-packages/keras/engine/training.py", line 1274, in predict_on_batch
outputs = self.predict_function(ins)
File "/home/han/.local/lib/python2.7/site-packages/keras/backend/theano_backend.py", line 717, in call
return self.function(*inputs)
File "/home/han/.local/lib/python2.7/site-packages/theano/compile/function_module.py", line 898, in call
storage_map=getattr(self.fn, 'storage_map', None))
File "/home/han/.local/lib/python2.7/site-packages/theano/gof/link.py", line 325, in raise_with_op
reraise(exc_type, exc_value, exc_trace)
File "/home/han/.local/lib/python2.7/site-packages/theano/compile/function_module.py", line 884, 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{half, (1, 1), (1, 1)}(InplaceDimShuffle{0,3,1,2}.0, Subtensor{::, ::, ::int64, ::int64}.0)
Toposort index: 1222
Inputs types: [TensorType(float32, (True, False, False, False)), TensorType(float32, 4D)]
Inputs shapes: [(1, 40, 512, 30), (1, 1, 512, 512)]
Inputs strides: [(160, 4, 4800, 160), (1048576, 1048576, -2048, -4)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Subtensor{int64:int64:int8, int64:int64:int8, int64:int64:int8, :int64:}(CorrMM{half, (1, 1), (1, 1)}.0, Constant{0}, Constant{1}, Constant{1}, ScalarFromTensor.0, ScalarFromTensor.0, Constant{1}, ScalarFromTensor.0, ScalarFromTensor.0, Constant{1}, Constant{30})]]

Backtrace when the node is created(use Theano flag traceback.limit=N to make it longer):
File "main.py", line 65, in
m = Model(input=[x, x_maps], output=sam_resnet([x, x_maps]))
File "/home/han/sam-master/models.py", line 136, in sam_resnet
nb_cols=3, nb_rows=3)(att_convlstm)
File "/home/han/.local/lib/python2.7/site-packages/keras/engine/topology.py", line 514, in call
self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
File "/home/han/.local/lib/python2.7/site-packages/keras/engine/topology.py", line 572, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/home/han/.local/lib/python2.7/site-packages/keras/engine/topology.py", line 149, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
File "/home/han/sam-master/attentive_convlstm.py", line 143, in call
initial_states = self.get_initial_states(x)
File "/home/han/sam-master/attentive_convlstm.py", line 42, in get_initial_states
initial_state = K.conv2d(initial_state, K.zeros((self.nb_filters_out, self.nb_filters_in, 1, 1)), border_mode='same')
File "/home/han/.local/lib/python2.7/site-packages/keras/backend/theano_backend.py", line 1135, 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.

[Abdulla-Al-Suman]

Hi @hhya1013, did you solved the problem?