Function download_pretrained_from_url

src/open_clip/pretrained.py:790–833

(
        url: str,
        cache_dir: Optional[str] = None,
)

def download_pretrained_from_url(
        url: str,
        cache_dir: Optional[str] = None,
):
    if not cache_dir:
        cache_dir = os.path.expanduser("~/.cache/clip")
    os.makedirs(cache_dir, exist_ok=True)
    filename = os.path.basename(url)

    if 'openaipublic' in url:
        expected_sha256 = url.split("/")[-2]
    elif 'mlfoundations' in url:
        expected_sha256 = os.path.splitext(filename)[0].split("-")[-1]
    else:
        expected_sha256 = ''

    download_target = os.path.join(cache_dir, filename)

    if os.path.exists(download_target) and not os.path.isfile(download_target):
        raise RuntimeError(f"{download_target} exists and is not a regular file")

    if os.path.isfile(download_target):
        if expected_sha256:
            if hashlib.sha256(open(download_target, "rb").read()).hexdigest().startswith(expected_sha256):
                return download_target
            else:
                warnings.warn(f"{download_target} exists, but the SHA256 checksum does not match; re-downloading the file")
        else:
            return download_target

    with urllib.request.urlopen(url) as source, open(download_target, "wb") as output:
        with tqdm(total=int(source.headers.get("Content-Length")), ncols=80, unit='iB', unit_scale=True) as loop:
            while True:
                buffer = source.read(8192)
                if not buffer:
                    break

                output.write(buffer)
                loop.update(len(buffer))

    if expected_sha256 and not hashlib.sha256(open(download_target, "rb").read()).hexdigest().startswith(expected_sha256):
        raise RuntimeError(f"Model has been downloaded but the SHA256 checksum does not not match")

    return download_target


def has_hf_hub(necessary=False):