[python pytorch]分享一些有用的代码片段

Github link

import numpy as np
import torch
import time
import random

随机数初始化

def set_random_seed(seed):
    """Set random seeds."""
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)

获取时间戳

def get_time_str():
    return time.strftime('%Y%m%d_%H%M%S', time.localtime())

扫描文件夹

def scandir(dir_path, suffix=None, recursive=False, full_path=False):
    """Scan a directory to find the interested files.

    Args:
        dir_path (str): Path of the directory.
        suffix (str | tuple(str), optional): File suffix that we are
            interested in. Default: None.
        recursive (bool, optional): If set to True, recursively scan the
            directory. Default: False.
        full_path (bool, optional): If set to True, include the dir_path.
            Default: False.

    Returns:
        A generator for all the interested files with relative paths.
    """
    
    if (suffix is not None) and not isinstance(suffix, (str, tuple)):
        raise TypeError('"suffix" must be a string or tuple of strings')
    
    root = dir_path
    
    def _scandir(dir_path, suffix, recursive):
        for entry in os.scandir(dir_path):
            if not entry.name.startswith('.') and entry.is_file():
                if full_path:
                    return_path = entry.path
                else:
                    return_path = osp.relpath(entry.path, root)
                
                if suffix is None:
                    yield return_path
                elif return_path.endswith(suffix):
                    yield return_path
            else:
                if recursive:
                    yield from _scandir(entry.path, suffix=suffix, recursive=recursive)
                else:
                    continue
    
    return _scandir(dir_path, suffix=suffix, recursive=recursive)

美化file size

def sizeof_fmt(size, suffix='B'):
    """Get human readable file size.

    Args:
        size (int): File size.
        suffix (str): Suffix. Default: 'B'.

    Return:
        str: Formatted file size.
    """
    for unit in ['', 'K', 'M', 'G', 'T', 'P', 'E', 'Z']:
        if abs(size) < 1024.0:
            return f'{size:3.1f} {unit}{suffix}'
        size /= 1024.0
    return f'{size:3.1f} Y{suffix}'

分布式（多GPU）初始化

# Modified from https://github.com/open-mmlab/mmcv/blob/master/mmcv/runner/dist_utils.py  # noqa: E501
import functools
import os
import subprocess
import torch
import torch.distributed as dist
import torch.multiprocessing as mp


def init_dist(launcher, backend='nccl', **kwargs):
    if mp.get_start_method(allow_none=True) is None:
        mp.set_start_method('spawn')
    if launcher == 'pytorch':
        _init_dist_pytorch(backend, **kwargs)
    elif launcher == 'slurm':
        _init_dist_slurm(backend, **kwargs)
    else:
        raise ValueError(f'Invalid launcher type: {launcher}')


def _init_dist_pytorch(backend, **kwargs):
    rank = int(os.environ['RANK'])
    num_gpus = torch.cuda.device_count()
    torch.cuda.set_device(rank % num_gpus)
    dist.init_process_group(backend=backend, **kwargs)


def _init_dist_slurm(backend, port=None):
    """Initialize slurm distributed training environment.

    If argument ``port`` is not specified, then the master port will be system
    environment variable ``MASTER_PORT``. If ``MASTER_PORT`` is not in system
    environment variable, then a default port ``29500`` will be used.

    Args:
        backend (str): Backend of torch.distributed.
        port (int, optional): Master port. Defaults to None.
    """
    proc_id = int(os.environ['SLURM_PROCID'])
    ntasks = int(os.environ['SLURM_NTASKS'])
    node_list = os.environ['SLURM_NODELIST']
    num_gpus = torch.cuda.device_count()
    torch.cuda.set_device(proc_id % num_gpus)
    addr = subprocess.getoutput(f'scontrol show hostname {node_list} | head -n1')
    # specify master port
    if port is not None:
        os.environ['MASTER_PORT'] = str(port)
    elif 'MASTER_PORT' in os.environ:
        pass  # use MASTER_PORT in the environment variable
    else:
        # 29500 is torch.distributed default port
        os.environ['MASTER_PORT'] = '29500'
    os.environ['MASTER_ADDR'] = addr
    os.environ['WORLD_SIZE'] = str(ntasks)
    os.environ['LOCAL_RANK'] = str(proc_id % num_gpus)
    os.environ['RANK'] = str(proc_id)
    dist.init_process_group(backend=backend)


def get_dist_info():
    if dist.is_available():
        initialized = dist.is_initialized()
    else:
        initialized = False
    if initialized:
        rank = dist.get_rank()
        world_size = dist.get_world_size()
    else:
        rank = 0
        world_size = 1
    return rank, world_size


def master_only(func):
    @functools.wraps(func)
    def wrapper(*args, **kwargs):
        rank, _ = get_dist_info()
        if rank == 0:
            return func(*args, **kwargs)
    
    return wrapper