general.py

from pathlib import Path
import glob
import re
from copy import deepcopy
import torch.nn as nn
import math
import torch
import os
import random
import numpy as np

def one_cycle(y1=0.0, y2=1.0, steps=100):
    # lambda function for sinusoidal ramp from y1 to y2 https://arxiv.org/pdf/1812.01187.pdf
    return lambda x: ((1 - math.cos(x * math.pi / steps)) / 2) * (y2 - y1) + y1


def init_seeds(seed=0):
    # Initialize random number generator (RNG) seeds https://pytorch.org/docs/stable/notes/randomness.html
    # cudnn seed 0 settings are slower and more reproducible, else faster and less reproducible
    import torch.backends.cudnn as cudnn
    random.seed(seed)
    np.random.seed(seed)
    
    torch.manual_seed(seed)
    ## cudnn.benchmark=False保证gpu每次都选择相同的算法，但是不保证该算法是deterministic的。
    cudnn.benchmark, cudnn.deterministic = (False, True) if seed == 0 else (True, False)


def is_parallel(model):
    # Returns True if model is of type DP or DDP
    return type(model) in (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel)


def de_parallel(model):
    # De-parallelize a model: returns single-GPU model if model is of type DP or DDP
    return model.module if is_parallel(model) else model

def copy_attr(a, b, include=(), exclude=()):
    # Copy attributes from b to a, options to only include [...] and to exclude [...]
    for k, v in b.__dict__.items():
        if (len(include) and k not in include) or k.startswith('_') or k in exclude:
            continue
        else:
            setattr(a, k, v)


def increment_path(path, exist_ok=False, sep='', mkdir=False):
    # Increment file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc.
    path = Path(path)  # os-agnostic
    if path.exists() and not exist_ok:
        path, suffix = (path.with_suffix(''), path.suffix) if path.is_file() else (path, '')
        dirs = glob.glob(f"{path}{sep}*")  # similar paths
        matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs]
        i = [int(m.groups()[0]) for m in matches if m]  # indices
        n = max(i) + 1 if i else 2  # increment number
        path = Path(f"{path}{sep}{n}{suffix}")  # increment path
    if mkdir:
        path.mkdir(parents=True, exist_ok=True)  # make directory
    return path


class ModelEMA:
    """ Model Exponential Moving Average from https://github.com/rwightman/pytorch-image-models
    Keep a moving average of everything in the model state_dict (parameters and buffers).
    This is intended to allow functionality like
    https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage
    A smoothed version of the weights is necessary for some training schemes to perform well.
    This class is sensitive where it is initialized in the sequence of model init,
    GPU assignment and distributed training wrappers.
    """

    def __init__(self, model, decay=0.9999, updates=0):
        # Create EMA
        self.ema = deepcopy(de_parallel(model)).eval()  # FP32 EMA

        # if next(model.parameters()).device.type != 'cpu':
        #     self.ema.half()  # FP16 EMA
        self.updates = updates  # number of EMA updates
        self.decay = lambda x: decay * (1 - math.exp(-x / 2000))  # decay exponential ramp (to help early epochs)
        for p in self.ema.parameters():
            p.requires_grad_(False)

    def update(self, model):
        # Update EMA parameters
        with torch.no_grad():
            self.updates += 1
            d = self.decay(self.updates)

            msd = de_parallel(model).state_dict()  # model state_dict
            for k, v in self.ema.state_dict().items():
                if v.dtype.is_floating_point:
                    v *= d
                    v += (1 - d) * msd[k].detach()

    def update_attr(self, model, include=(), exclude=('process_group', 'reducer')):
        # Update EMA attributes
        copy_attr(self.ema, model, include, exclude)



def select_device(device='', batch_size=0, newline=True):
    # device = 'cpu' or '0' or '0,1,2,3'
    s = f'torch {torch.__version__} '  # string
    device = str(device).strip().lower().replace('cuda:', '')  # to string, 'cuda:0' to '0'
    cpu = device == 'cpu'
    if cpu:
        os.environ['CUDA_VISIBLE_DEVICES'] = '-1'  # force torch.cuda.is_available() = False
    elif device:  # non-cpu device requested
        os.environ['CUDA_VISIBLE_DEVICES'] = device  # set environment variable - must be before assert is_available()
        assert torch.cuda.is_available() and torch.cuda.device_count() >= len(device.replace(',', '')), \
            f"Invalid CUDA '--device {device}' requested, use '--device cpu' or pass valid CUDA device(s)"

    cuda = not cpu and torch.cuda.is_available()
    if cuda:
        devices = device.split(',') if device else '0'  # range(torch.cuda.device_count())  # i.e. 0,1,6,7
        n = len(devices)  # device count
        if n > 1 and batch_size > 0:  # check batch_size is divisible by device_count
            assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}'
        space = ' ' * (len(s) + 1)
        for i, d in enumerate(devices):
            p = torch.cuda.get_device_properties(i)
            s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / 1024 ** 2:.0f}MiB)\n"  # bytes to MB
    else:
        s += 'CPU\n'

    if not newline:
        s = s.rstrip()
    return torch.device('cuda:0' if cuda else 'cpu')