utils/misc.py

# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
"""
Misc functions, including distributed helpers.

Mostly copy-paste from torchvision references.
"""
import logging
import sys
import os
import time
import datetime
from subprocess import call
import subprocess
from collections import defaultdict, deque
import pickle
from packaging import version
from typing import Optional, List

import torch
import torchvision
import torch.distributed as dist
from torch import Tensor

if version.parse(torchvision.__version__) < version.parse('0.7'):
    from torchvision.ops import _new_empty_tensor
    from torchvision.ops.misc import _output_size


def print_cuda_statistics():
    logger = logging.getLogger("System")
    logger.info('__Python VERSION:  {}'.format(sys.version))
    logger.info('__pyTorch VERSION:  {}'.format(torch.__version__))
    logger.info('__CUDA VERSION')
    # call(["nvcc", "--version"])
    logger.info('__CUDNN VERSION:  {}'.format(torch.backends.cudnn.version()))
    logger.info('__Number CUDA Devices:  {}'.format(torch.cuda.device_count()))
    logger.info('__Devices')
    call(["nvidia-smi", "--format=csv",
          "--query-gpu=index,name,driver_version,memory.total,memory.used,memory.free"])
    logger.info('Active CUDA Device: GPU {}'.format(torch.cuda.current_device()))
    logger.info('Available devices  {}'.format(torch.cuda.device_count()))
    logger.info('Current cuda device  {}'.format(torch.cuda.current_device()))


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)


def all_gather(data):
    """
    Run all_gather on arbitrary picklable data (not necessarily tensors)
    Args:
        data: any picklable object
    Returns:
        list[data]: list of data gathered from each rank
    """
    world_size = get_world_size()
    if world_size == 1:
        return [data]

    # serialized to a Tensor
    buffer = pickle.dumps(data)
    storage = torch.ByteStorage.from_buffer(buffer)
    tensor = torch.ByteTensor(storage).to("cuda")

    # obtain Tensor size of each rank
    local_size = torch.tensor([tensor.numel()], device="cuda")
    size_list = [torch.tensor([0], device="cuda") for _ in range(world_size)]
    dist.all_gather(size_list, local_size)
    size_list = [int(size.item()) for size in size_list]
    max_size = max(size_list)

    # receiving Tensor from all ranks
    # we pad the tensor because torch all_gather does not support
    # gathering tensors of different shapes
    tensor_list = []
    for _ in size_list:
        tensor_list.append(torch.empty((max_size,), dtype=torch.uint8, device="cuda"))
    if local_size != max_size:
        padding = torch.empty(size=(max_size - local_size,), dtype=torch.uint8, device="cuda")
        tensor = torch.cat((tensor, padding), dim=0)
    dist.all_gather(tensor_list, tensor)

    data_list = []
    for size, tensor in zip(size_list, tensor_list):
        buffer = tensor.cpu().numpy().tobytes()[:size]
        data_list.append(pickle.loads(buffer))

    return data_list


def reduce_dict(input_dict, average=True):
    """
    Args:
        input_dict (dict): all the values will be reduced
        average (bool): whether to do average or sum
    Reduce the values in the dictionary from all processes so that all processes
    have the averaged results. Returns a dict with the same fields as
    input_dict, after reduction.
    """
    world_size = get_world_size()
    if world_size < 2:
        return input_dict
    with torch.no_grad():
        names = []
        values = []
        # sort the keys so that they are consistent across processes
        for k in sorted(input_dict.keys()):
            names.append(k)
            values.append(input_dict[k])
        values = torch.stack(values, dim=0)
        dist.all_reduce(values)
        if average:
            values /= world_size
        reduced_dict = {k: v for k, v in zip(names, values)}
    return reduced_dict


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.detach().cpu().item()
            if isinstance(v, float):
                v = {'value': v, 'n': 1}
            # assert isinstance(v, dict) and isinstance(v['value'], float) and isinstance(v['n'], 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 print_avg(self):
        loss_str = []
        for name, meter in self.meters.items():
            loss_str.append(
                "{}: {}".format(name, str(meter.global_avg))
            )
        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'
        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
        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 get_sha():
    cwd = os.path.dirname(os.path.abspath(__file__))

    def _run(command):
        return subprocess.check_output(command, cwd=cwd).decode('ascii').strip()
    sha = 'N/A'
    diff = "clean"
    branch = 'N/A'
    try:
        sha = _run(['git', 'rev-parse', 'HEAD'])
        subprocess.check_output(['git', 'diff'], cwd=cwd)
        diff = _run(['git', 'diff-index', 'HEAD'])
        diff = "has uncommited changes" if diff else "clean"
        branch = _run(['git', 'rev-parse', '--abbrev-ref', 'HEAD'])
    except Exception:
        pass
    message = f"sha: {sha}, status: {diff}, branch: {branch}"
    return message


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



def set_logger(file_path):
    logger = logging.getLogger()
    logger.setLevel('INFO')
    stream_handler = logging.StreamHandler()
    file_handler = logging.FileHandler(file_path, 'w')
    formatter = logging.Formatter('[%(asctime)s] %(message)s', '%m-%d %H:%M:%S')
    for handler in [stream_handler, file_handler]:
        handler.setFormatter(formatter)
        handler.setLevel('INFO')
        logger.addHandler(handler)
    return logger


def set_save_dir(save_dir, log_name, replace=True):
    logger = set_logger(os.path.join(save_dir, f'log_{log_name}.txt'))
    return logger