Closed GodsDusk closed 2 years ago
I think up_2 = tf.image.resize_nearest_neighbor(low_3, tf.shape(low_3)[1:3]*2, name = 'upsampling')
should be
up_2 = tf.image.resize_nearest_neighbor(low_3, tf.shape(up_1)[1:3], name = 'upsampling')
so it could handle those input size is not 2^n
You are right. Thank you for your update I will modify this.
This could be replace by : up_2 = tf.image.resize_nearest_neighbor(low_3, [(2**(n+1))*2, (2**(n+1))*2], name = 'upsampling')
up_2 = tf.image.resize_nearest_neighbor(low_3, [(2**(n+1))*2, (2**(n+1))*2], name = 'upsampling')
I think up_2 = tf.image.resize_nearest_neighbor(low_3, tf.shape(low_3)[1:3]*2, name = 'upsampling')
should be
up_2 = tf.image.resize_nearest_neighbor(low_3, tf.shape(up_1)[1:3], name = 'upsampling')
so it could handle those input size is not 2^n