In prepare_data.py I found the following code:
train_lable_distribution.append([pre_vote_image_name, en_im_path, ld])
Here pre_vote_image_name and ld are not changed inside the loop. So its essentially adding the same thing over and over again in the training data but the enhanced image is different.
In
prepare_data.pyI found the following code:Here
pre_vote_image_nameandldare not changed inside the loop. So its essentially adding the same thing over and over again in the training data but the enhanced image is different.