Retrain the model to obtain 2X of the out[0]

[Elwarfalli]

Hi @JingqingZ I'd like to retrain the mode to get 2x instead of 4x. Would you mind help me what should I change in the code??

I download Data 2x

I changed the dimenstion of : t_target_image = tf.placeholder('float32', [batch_size, 192, 192, 3], name='t_target_image').

so I am getting this error: ValueError: Trying to share variable SRGAN_d/ho/dense/W, but specified shape (18432, 1) and found shape (4608, 1).