utils.py

import os
import torch
import logging
import datetime
from collections import defaultdict, deque


def get_timestamp():
    return datetime.datetime.now().strftime("%y%m%d-%H%M%S")


def get_logger(name, root, level=logging.INFO, screen=False, tofile=True):
    """get logger"""
    logger = logging.getLogger(name)
    formatter = logging.Formatter(
        "%(asctime)s.%(msecs)03d - %(levelname)s: %(message)s",
        datefmt="%y-%m-%d %H:%M:%S",
    )
    logger.setLevel(level)
    if tofile:
        log_file = os.path.join(root, name + "_{}.log".format(get_timestamp()))
        fh = logging.FileHandler(log_file, mode="w")
        fh.setFormatter(formatter)
        logger.addHandler(fh)
    if screen:
        sh = logging.StreamHandler()
        sh.setFormatter(formatter)
        logger.addHandler(sh)
    return logger


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

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

    def log_every(self, step, total_steps, datatime, itertime, print_freq, header=None):
        if not header:
            header = ""
        iter_time = SmoothedValue(fmt="{avg:.4f}")
        data_time = SmoothedValue(fmt="{avg:.4f}")
        space_fmt = ":" + str(len(str(total_steps))) + "d"
        if torch.cuda.is_available():
            log_msg = self.delimiter.join(
                [
                    header,
                    "[{0" + space_fmt + "}/{1}]",
                    "eta: {eta}",
                    "{meters}",
                    "time: {time}",
                    "data: {data}",
                    "max mem: {memory:.0f}",
                ]
            )
        else:
            log_msg = self.delimiter.join(
                [
                    header,
                    "[{0" + space_fmt + "}/{1}]",
                    "eta: {eta}",
                    "{meters}",
                    "time: {time}",
                    "data: {data}",
                ]
            )
        MB = 1024.0 * 1024.0
        data_time.update(datatime)
        iter_time.update(itertime)
        if step % print_freq == 0 or step == total_steps - 1:
            eta_seconds = iter_time.global_avg * (total_steps - step)
            eta_string = str(datetime.timedelta(seconds=int(eta_seconds)))
            if torch.cuda.is_available():
                print(
                    log_msg.format(
                        step,
                        total_steps,
                        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(
                        step,
                        total_steps,
                        eta=eta_string,
                        meters=str(self),
                        time=str(iter_time),
                        data=str(data_time),
                    )
                )