question about def deconv in model_pwcnet.py

[xuleyoung]

In general, we use odd kernel size in conv or deconv, def deonv(line 1182) in model_pwcnet.py , I think the kernel_size=3,not 4.
return tf.layers.conv2d_transpose(x, 2, 4, 2, 'same', name=op_name)