ValueError: Dimension 1 in both shapes must be equal, but are 256 and 16. Shapes are [1,256,256] and [1,16,16]. for 'concat_1' (op: 'ConcatV2') with input shapes: [1,256,256,4], [1,16,16,3], [] and with computed input tensors: input[2] = <3>.

[Auroratan]

self.real_AB = tf.concat(axis=3, values=[combined_preimage, self.real_images]) self.fake_AB = tf.concat(axis=3, values=[combined_preimage, self.generated_images])

That is mistake,what should i do ?