ValueError: CorrMM images and kernel must have the same stack size

[ghost]

Traceback (most recent call last): File "/home/cbl/PycharmProjects/Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model/main.py", line 155, in predictions = m.predict_generator(generator_test(b_s=b_s, imgs_test_path=imgs_test_path), nb_imgs_test)[0] File "/home/public/anaconda3/envs/py27/lib/python2.7/site-packages/keras/engine/training.py", line 1634, in predict_generator outs = self.predict_on_batch(x) File "/home/public/anaconda3/envs/py27/lib/python2.7/site-packages/keras/engine/training.py", line 1274, in predict_on_batch outputs = self.predict_function(ins) File "/home/public/anaconda3/envs/py27/lib/python2.7/site-packages/keras/backend/theano_backend.py", line 717, in call return self.function(*inputs) File "/home/public/anaconda3/envs/py27/lib/python2.7/site-packages/theano/compile/function_module.py", line 917, in call storage_map=getattr(self.fn, 'storage_map', None)) File "/home/public/anaconda3/envs/py27/lib/python2.7/site-packages/theano/gof/link.py", line 325, in raise_with_op reraise(exc_type, exc_value, exc_trace) File "/home/public/anaconda3/envs/py27/lib/python2.7/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{half, (1, 1), (1, 1), 1 False}(InplaceDimShuffle{0,3,1,2}.0, Subtensor{::, ::, ::int64, ::int64}.0) Toposort index: 251 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), 1 False}.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 "/home/cbl/PycharmProjects/Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model/main.py", line 104, in m = Model(input=[x, x_maps], output=sam_vgg([x, x_maps])) File "/home/cbl/PycharmProjects/Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model/models.py", line 107, in sam_vgg nb_cols=3, nb_rows=3)(att_convlstm) File "/home/public/anaconda3/envs/py27/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/public/anaconda3/envs/py27/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/public/anaconda3/envs/py27/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/cbl/PycharmProjects/Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model/attentive_convlstm.py", line 149, in call initial_states = self.get_initial_states(x) File "/home/cbl/PycharmProjects/Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model/attentive_convlstm.py", line 43, 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/public/anaconda3/envs/py27/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.

[ghost]

when I test ,it account this problem,please help me,thanks

[hhya1013]

I also account this problem ,Now have you solved this problem ?If you solved it,please help me ,thanks.