437 lines
13 KiB
Python
437 lines
13 KiB
Python
# This file is part of COAT, and is distributed under the
|
|
# OSI-approved BSD 3-Clause License. See top-level LICENSE file or
|
|
# https://github.com/Kitware/COAT/blob/master/LICENSE for details.
|
|
|
|
import datetime
|
|
import errno
|
|
import json
|
|
import os
|
|
import os.path as osp
|
|
import pickle
|
|
import random
|
|
import time
|
|
from collections import defaultdict, deque
|
|
|
|
import numpy as np
|
|
import torch
|
|
import torch.distributed as dist
|
|
from tabulate import tabulate
|
|
|
|
|
|
# -------------------------------------------------------- #
|
|
# 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
|
|
|
|
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"
|
|
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)
|
|
)
|
|
)
|
|
|
|
|
|
# -------------------------------------------------------- #
|
|
# Distributed training #
|
|
# -------------------------------------------------------- #
|
|
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):
|
|
"""
|
|
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.
|
|
|
|
Args:
|
|
input_dict (dict): all the values will be reduced
|
|
average (bool): whether to do average or sum
|
|
"""
|
|
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
|
|
|
|
|
|
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 init_distributed_mode(args):
|
|
if "RANK" in os.environ and "WORLD_SIZE" in os.environ:
|
|
args.rank = int(os.environ["RANK"])
|
|
args.world_size = int(os.environ["WORLD_SIZE"])
|
|
args.gpu = int(os.environ["LOCAL_RANK"])
|
|
elif "SLURM_PROCID" in os.environ:
|
|
args.rank = int(os.environ["SLURM_PROCID"])
|
|
args.gpu = args.rank % torch.cuda.device_count()
|
|
else:
|
|
print("Not using distributed mode")
|
|
args.distributed = False
|
|
return
|
|
|
|
args.distributed = True
|
|
|
|
torch.cuda.set_device(args.gpu)
|
|
args.dist_backend = "nccl"
|
|
print("| distributed init (rank {}): {}".format(args.rank, args.dist_url), flush=True)
|
|
torch.distributed.init_process_group(
|
|
backend=args.dist_backend,
|
|
init_method=args.dist_url,
|
|
world_size=args.world_size,
|
|
rank=args.rank,
|
|
)
|
|
torch.distributed.barrier()
|
|
setup_for_distributed(args.rank == 0)
|
|
|
|
|
|
# -------------------------------------------------------- #
|
|
# File operation #
|
|
# -------------------------------------------------------- #
|
|
def filename(path):
|
|
return osp.splitext(osp.basename(path))[0]
|
|
|
|
|
|
def mkdir(path):
|
|
try:
|
|
os.makedirs(path)
|
|
except OSError as e:
|
|
if e.errno != errno.EEXIST:
|
|
raise
|
|
|
|
|
|
def read_json(fpath):
|
|
with open(fpath, "r") as f:
|
|
obj = json.load(f)
|
|
return obj
|
|
|
|
|
|
def write_json(obj, fpath):
|
|
mkdir(osp.dirname(fpath))
|
|
_obj = obj.copy()
|
|
for k, v in _obj.items():
|
|
if isinstance(v, np.ndarray):
|
|
_obj.pop(k)
|
|
with open(fpath, "w") as f:
|
|
json.dump(_obj, f, indent=4, separators=(",", ": "))
|
|
|
|
|
|
def symlink(src, dst, overwrite=True, **kwargs):
|
|
if os.path.lexists(dst) and overwrite:
|
|
os.remove(dst)
|
|
os.symlink(src, dst, **kwargs)
|
|
|
|
|
|
# -------------------------------------------------------- #
|
|
# Misc #
|
|
# -------------------------------------------------------- #
|
|
def create_small_table(small_dict):
|
|
"""
|
|
Create a small table using the keys of small_dict as headers. This is only
|
|
suitable for small dictionaries.
|
|
|
|
Args:
|
|
small_dict (dict): a result dictionary of only a few items.
|
|
|
|
Returns:
|
|
str: the table as a string.
|
|
"""
|
|
keys, values = tuple(zip(*small_dict.items()))
|
|
table = tabulate(
|
|
[values],
|
|
headers=keys,
|
|
tablefmt="pipe",
|
|
floatfmt=".3f",
|
|
stralign="center",
|
|
numalign="center",
|
|
)
|
|
return table
|
|
|
|
|
|
def warmup_lr_scheduler(optimizer, warmup_iters, warmup_factor):
|
|
def f(x):
|
|
if x >= warmup_iters:
|
|
return 1
|
|
alpha = float(x) / warmup_iters
|
|
return warmup_factor * (1 - alpha) + alpha
|
|
|
|
return torch.optim.lr_scheduler.LambdaLR(optimizer, f)
|
|
|
|
|
|
def resume_from_ckpt(ckpt_path, model, optimizer=None, lr_scheduler=None):
|
|
ckpt = torch.load(ckpt_path)
|
|
model.load_state_dict(ckpt["model"], strict=False)
|
|
if optimizer is not None:
|
|
optimizer.load_state_dict(ckpt["optimizer"])
|
|
if lr_scheduler is not None:
|
|
lr_scheduler.load_state_dict(ckpt["lr_scheduler"])
|
|
print(f"loaded checkpoint {ckpt_path}")
|
|
print(f"model was trained for {ckpt['epoch']} epochs")
|
|
return ckpt["epoch"]
|
|
|
|
|
|
def set_random_seed(seed):
|
|
torch.manual_seed(seed)
|
|
torch.cuda.manual_seed(seed)
|
|
torch.cuda.manual_seed_all(seed)
|
|
torch.backends.cudnn.benchmark = False
|
|
torch.backends.cudnn.deterministic = True
|
|
random.seed(seed)
|
|
np.random.seed(seed)
|
|
os.environ["PYTHONHASHSEED"] = str(seed)
|