utils/misc.py

import datetime
import functools
import os

import torch
import torch.distributed as dist
import timm.models.hub as timm_hub

def setup_for_distributed(is_master):
    """
    This function disables printing when not in master process
    """
    import builtins as __builtin__

    builtin_print = __builtin__.print

    def print(*args, **kwargs):
        force = kwargs.pop("force", False)
        if is_master or force:
            builtin_print(*args, **kwargs)

    __builtin__.print = print


def is_dist_avail_and_initialized():
    if not dist.is_available():
        return False
    if not dist.is_initialized():
        return False
    return True


def get_world_size():
    if not is_dist_avail_and_initialized():
        return 1
    return dist.get_world_size()


def get_rank():
    if not is_dist_avail_and_initialized():
        return 0
    return dist.get_rank()


def is_main_process():
    return get_rank() == 0



def download_cached_file(url, check_hash=True, progress=False):
    """
    Download a file from a URL and cache it locally. If the file already exists, it is not downloaded again.
    If distributed, only the main process downloads the file, and the other processes wait for the file to be downloaded.
    """
    if not url.startswith('http'):
        return url

    def get_cached_file_path():
        # a hack to sync the file path across processes
        parts = torch.hub.urlparse(url)
        filename = os.path.basename(parts.path)
        cached_file = os.path.join(timm_hub.get_cache_dir(), filename)

        return cached_file

    if is_main_process():
        timm_hub.download_cached_file(url, check_hash, progress)


    return get_cached_file_path()