7d9db23a389499c2764fb850cd19f853cc3e8565,ludwig/features/image_feature.py,ImageBaseFeature,add_feature_data,#Any#Any#Any#Any#Any#,192

Before Change

                (num_images, height, width, num_channels),
                dtype=np.uint8
            )
            for i in range(len(dataset_df)):
                filepath = get_abs_path(
                    csv_path,
                    dataset_df[feature["name"]][i]
                )

                img = ImageBaseFeature._read_image_and_resize(
                    filepath,
                    width,
                    height,
                    should_resize,
                    num_channels,
                    preprocessing_parameters["resize_method"],
                    user_specified_num_channels
                )
                try:
                    data[feature["name"]][i, :, :, :] = img
                except:
                    logger.error(
                        "Images are not of the same size. "
                        "Expected size is {}, "
                        "current image size is {}."
                        "Images are expected to be all of the same size"
                        "or explicit image width and height are expected"
                        "to be provided. "
                        "Additional information: https://uber.github.io/ludwig/user_guide///image-features-preprocessing"
                            .format(first_image.shape, img.shape)
                    )
                    raise
        else:
            data_fp = os.path.splitext(dataset_df.csv)[0] + ".hdf5"
            mode = "w"
            if os.path.isfile(data_fp):
                mode = "r+"
            with h5py.File(data_fp, mode) as h5_file:
                image_dataset = h5_file.create_dataset(
                    feature["name"] + "_data",
                    (num_images, height, width, num_channels),
                    dtype=np.uint8
                )
                for i in range(len(dataset_df)):
                    filepath = get_abs_path(
                        csv_path,
                        dataset_df[feature["name"]][i]

After Change

                (num_images, height, width, num_channels),
                dtype=np.uint8
            )
            with Pool(5) as pool:
                logger.info("Using 5 processes for preprocessing images")
                data[feature["name"]] = np.array(
                    pool.map(read_image_and_resize, all_file_paths)
                )
        else:
            data_fp = os.path.splitext(dataset_df.csv)[0] + ".hdf5"
            mode = "w"
            if os.path.isfile(data_fp):

Instances