Open joschkazj opened 6 years ago
I tried training the model for grayscale input and was having similar issues as mentioned in #12, setting input_c_dim=1 and output_c_dim=1 did not work for me
input_c_dim=1
output_c_dim=1
model = pix2pix(sess, image_size=args.fine_size, batch_size=args.batch_size, output_size=args.fine_size, dataset_name=args.dataset_name, checkpoint_dir=args.checkpoint_dir, sample_dir=args.sample_dir, input_c_dim=1, output_c_dim=1)
After investigating the issue, I changed the image loading function which made the optional reshaping
if (self.is_grayscale): batch_images = np.array(batch).astype(np.float32)[:, :, :, None] else: batch_images = np.array(batch).astype(np.float32)
obsolete.
I tried training the model for grayscale input and was having similar issues as mentioned in #12, setting
input_c_dim=1
andoutput_c_dim=1
did not work for meAfter investigating the issue, I changed the image loading function which made the optional reshaping
obsolete.