finetune_instruct_pix2pix.py [743:757]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
        # We need to ensure that the original and the edited images undergo the same
        # augmentation transforms.
        images = np.concatenate([original_images, edited_images])
        images = torch.tensor(images)
        images = 2 * (images / 255) - 1
        return train_transforms(images)

    def preprocess_train(examples):
        # Preprocess images.
        preprocessed_images = preprocess_images(examples)
        # Since the original and edited images were concatenated before
        # applying the transformations, we need to separate them and reshape
        # them accordingly.
        original_images, edited_images = preprocessed_images.chunk(2)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



train_instruct_pix2pix.py [654:668]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
        # We need to ensure that the original and the edited images undergo the same
        # augmentation transforms.
        images = np.concatenate([original_images, edited_images])
        images = torch.tensor(images)
        images = 2 * (images / 255) - 1
        return train_transforms(images)

    def preprocess_train(examples):
        # Preprocess images.
        preprocessed_images = preprocess_images(examples)
        # Since the original and edited images were concatenated before
        # applying the transformations, we need to separate them and reshape
        # them accordingly.
        original_images, edited_images = preprocessed_images.chunk(2)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -