The model expects 2 input arrays, but only received one array.

[LLCF]

I have updated this code to Keras2, but met a problem.

with tf.device('/cpu:0'):
	merged = outputs_all[0]
	for outputs in outputs_all[1:]:
		print(outputs)
		merged.append(K.concatenate(outputs, axis=0))
	print(merged)

print

[<tf.Tensor 'tower_0/sequential_1/dropout_2/cond/Merge:0' shape=(?, 101) dtype=float32>, <tf.Tensor 'tower_1/sequential_1/dropout_2/cond/Merge:0' shape=(?, 101) dtype=float32>]

and got an error

ValueError: The model expects 2 input arrays, but only received one array. Found: array with shape (48, 101)

Could I merge two tf.Tensors to one tf.Tensor?

[bzamecnik]

merged contains a list of merged outputs (since the basic model can have multiple outputs. Each output should be a single Tensor concatenated from the replicas. In this case it seems that the replica outputs were not concatenated together (each element in the list contains a Tensor from a different replica).

What looks a bit strange is the usage of K.concatenate() instead of keras.layers.merge.concatenate().