1ef3ad90a3423ed15ca41e0ea4e81012ebe84a9f,catalyst/data/scripts/project_embeddings.py,,main,#Any#Any#,88

Before Change

    if args.img_col is not None:
        image_names = [
            path.join(args.img_rootpath, name)
            for name in df[args.img_col].values
        ]
        img_data = np.stack(
            [load_image(name, args.img_size) for name in image_names], axis=0
        )
        img_data = (
            img_data.transpose((0, 3, 1, 2)) / 255.0  // noqa: WPS432
        ).astype(np.float32)
        img_data = torch.from_numpy(img_data)
    else:
        img_data = None

After Change

    if args.num_rows is not None:
        indices = np.random.choice(len(df), args.num_rows)
        features = features[indices, :]
        df = df.iloc[indices]

    if args.img_col is not None:
        img_data = _load_image_data(
            rootpath=args.img_rootpath, paths=df[args.img_col].values
        )
    else:
        img_data = None

    summary_writer = SummaryWriter(args.out_dir)
    metadata = df[meta_header].values.tolist()
    metadata = [
        [
            str(text)
            .replace("\n", " ")
            .replace(r"\s", " ")
            .replace(r"\s\s+", " ")
            .strip()
            for text in texts
        ]
        for texts in metadata
    ]
    assert len(metadata) == len(features)
    summary_writer.add_embedding(
        features,
        metadata=metadata,

Instances