misc.py

# Copyright (c) 2015-present, Facebook, Inc.
# All rights reserved.
"""
Misc functions, including distributed helpers.

Mostly copy-paste from torchvision references.
"""
import os
import time
import torch
import shutil
import datetime
from enum import Enum
from collections import defaultdict, deque
from .dist import is_dist_avail_and_initialized, is_main_process
import torch.distributed as dist

class SmoothedValue(object):
    """Track a series of values and provide access to smoothed values over a
    window or the global series average.
    """

    def __init__(self, window_size=20, fmt=None):
        if fmt is None:
            fmt = "{median:.4f} ({global_avg:.4f})"
        self.deque = deque(maxlen=window_size)
        self.total = 0.0
        self.count = 0
        self.fmt = fmt

    def update(self, value, n=1):
        self.deque.append(value)
        self.count += n
        self.total += value * n

    def synchronize_between_processes(self):
        """
        Warning: does not synchronize the deque!
        """
        if not is_dist_avail_and_initialized():
            return
        t = torch.tensor([self.count, self.total], dtype=torch.float64, device='cuda')
        dist.barrier()
        dist.all_reduce(t)
        t = t.tolist()
        self.count = int(t[0])
        self.total = t[1]

    @property
    def median(self):
        d = torch.tensor(list(self.deque))
        return d.median().item()

    @property
    def avg(self):
        d = torch.tensor(list(self.deque), dtype=torch.float32)
        return d.mean().item()

    @property
    def global_avg(self):
        return self.total / self.count

    @property
    def max(self):
        return max(self.deque)

    @property
    def value(self):
        return self.deque[-1]

    def __str__(self):
        return self.fmt.format(
            median=self.median,
            avg=self.avg,
            global_avg=self.global_avg,
            max=self.max,
            value=self.value)


class MetricLogger(object):
    def __init__(self, delimiter="\t"):
        self.meters = defaultdict(SmoothedValue)
        self.delimiter = delimiter

    def update(self, **kwargs):
        for k, v in kwargs.items():
            if isinstance(v, torch.Tensor):
                v = v.item()
            assert isinstance(v, (float, int))
            self.meters[k].update(v)

    def __getattr__(self, attr):
        if attr in self.meters:
            return self.meters[attr]
        if attr in self.__dict__:
            return self.__dict__[attr]
        raise AttributeError("'{}' object has no attribute '{}'".format(
            type(self).__name__, attr))

    def __str__(self):
        loss_str = []
        for name, meter in self.meters.items():
            loss_str.append(
                "{}: {}".format(name, str(meter))
            )
        return self.delimiter.join(loss_str)

    def synchronize_between_processes(self):
        for meter in self.meters.values():
            meter.synchronize_between_processes()

    def add_meter(self, name, meter):
        self.meters[name] = meter

    def log_every(self, iterable, print_freq, header=None):
        i = 0
        if not header:
            header = ''
        start_time = time.time()
        end = time.time()
        iter_time = SmoothedValue(fmt='{avg:.4f}')
        data_time = SmoothedValue(fmt='{avg:.4f}')
        space_fmt = ':' + str(len(str(len(iterable)))) + 'd'
        log_msg = [
            header,
            '[{0' + space_fmt + '}/{1}]',
            'eta: {eta}',
            '{meters}',
            'time: {time}',
            'data: {data}'
        ]
        if torch.cuda.is_available():
            log_msg.append('max mem: {memory:.0f}')
        log_msg = self.delimiter.join(log_msg)
        MB = 1024.0 * 1024.0
        for obj in iterable:
            data_time.update(time.time() - end)
            yield obj
            iter_time.update(time.time() - end)
            if i % print_freq == 0 or i == len(iterable) - 1:
                eta_seconds = iter_time.global_avg * (len(iterable) - i)
                eta_string = str(datetime.timedelta(seconds=int(eta_seconds)))
                if torch.cuda.is_available():
                    print(log_msg.format(
                        i, len(iterable), eta=eta_string,
                        meters=str(self),
                        time=str(iter_time), data=str(data_time),
                        memory=torch.cuda.max_memory_allocated() / MB))
                else:
                    print(log_msg.format(
                        i, len(iterable), eta=eta_string,
                        meters=str(self),
                        time=str(iter_time), data=str(data_time)))
            i += 1
            end = time.time()
        total_time = time.time() - start_time
        total_time_str = str(datetime.timedelta(seconds=int(total_time)))
        print('{} Total time: {} ({:.4f} s / it)'.format(
            header, total_time_str, total_time / len(iterable)))


def save_on_master(*args, **kwargs):
    if is_main_process():
        torch.save(*args, **kwargs)

class Summary(Enum):
    NONE = 0
    AVERAGE = 1
    SUM = 2
    COUNT = 3

class AverageMeter(object):
    """Computes and stores the average and current value"""
    def __init__(self, name, fmt=':f', summary_type=Summary.AVERAGE):
        self.name = name
        self.fmt = fmt
        self.summary_type = summary_type
        self.reset()

    def reset(self):
        self.val = 0
        self.avg = 0
        self.sum = 0
        self.count = 0

    def update(self, val, n=1):
        self.val = val
        self.sum += val * n
        self.count += n
        self.avg = self.sum / self.count

    def all_reduce(self):
        if torch.cuda.is_available():
            device = torch.device("cuda")
        elif torch.backends.mps.is_available():
            device = torch.device("mps")
        else:
            device = torch.device("cpu")
        total = torch.tensor([self.sum, self.count], dtype=torch.float32, device=device)
        dist.all_reduce(total, dist.ReduceOp.SUM, async_op=False)
        self.sum, self.count = total.tolist()
        self.avg = self.sum / self.count

    def __str__(self):
        fmtstr = '{name} {val' + self.fmt + '} ({avg' + self.fmt + '})'
        return fmtstr.format(**self.__dict__)
    
    def summary(self):
        fmtstr = ''
        if self.summary_type is Summary.NONE:
            fmtstr = ''
        elif self.summary_type is Summary.AVERAGE:
            fmtstr = '{name} {avg:.3f}'
        elif self.summary_type is Summary.SUM:
            fmtstr = '{name} {sum:.3f}'
        elif self.summary_type is Summary.COUNT:
            fmtstr = '{name} {count:.3f}'
        else:
            raise ValueError('invalid summary type %r' % self.summary_type)
        
        return fmtstr.format(**self.__dict__)


class ProgressMeter(object):
    def __init__(self, num_batches, meters, prefix=""):
        self.batch_fmtstr = self._get_batch_fmtstr(num_batches)
        self.meters = meters
        self.prefix = prefix

    def display(self, batch, lr, remaining_time):
        entries = [self.prefix + self.batch_fmtstr.format(batch)]
        entries += ["ETA: {:02d}:{:02d}:{:02d}".format(*remaining_time)]
        entries += ["LR: {:.8f}".format(lr)]
        entries += [str(meter) for meter in self.meters]
        print('\t'.join(entries))
        
    def display_summary(self):
        entries = [" *"]
        entries += [meter.summary() for meter in self.meters]
        print(' '.join(entries))

    def _get_batch_fmtstr(self, num_batches):
        num_digits = len(str(num_batches // 1))
        fmt = '{:' + str(num_digits) + 'd}' # define the format of the number
        return '[' + fmt + '/' + fmt.format(num_batches) + ']'

def sec_2_hms(secs):
    h = secs//(60*60)
    m = (secs - h*60*60)//60
    s = secs - (h*60*60) - (m*60)
    return h, m, s

def save_config(config, name):
    shutil.copyfile(config.yaml_file, os.path.join(name, "train_config_file.yaml")  )
    config_dict = vars(config)
    torch.save(  config_dict,  os.path.join(name, "config_dict.pth")     )
    return config_dict