330 lines
10 KiB
Python
330 lines
10 KiB
Python
|
import datetime
|
|||
|
|
import errno
|
|||
|
|
import os
|
|||
|
|
import time
|
|||
|
|
from collections import defaultdict, deque
|
|||
|
|
|
|||
|
|
import torch
|
|||
|
|
import torch.distributed as dist
|
|||
|
|
|
|||
|
|
|
|||
|
|
class SmoothedValue:
|
|||
|
|
"""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!
|
|||
|
|
"""
|
|||
|
|
t = reduce_across_processes([self.count, self.total])
|
|||
|
|
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 ConfusionMatrix:
|
|||
|
|
def __init__(self, num_classes):
|
|||
|
|
self.num_classes = num_classes
|
|||
|
|
self.mat = None
|
|||
|
|
|
|||
|
|
def update(self, a, b):
|
|||
|
|
n = self.num_classes
|
|||
|
|
if self.mat is None:
|
|||
|
|
self.mat = torch.zeros((n, n), dtype=torch.int64, device=a.device)
|
|||
|
|
with torch.inference_mode():
|
|||
|
|
k = (a >= 0) & (a < n)
|
|||
|
|
inds = n * a[k].to(torch.int64) + b[k]
|
|||
|
|
self.mat += torch.bincount(inds, minlength=n**2).reshape(n, n)
|
|||
|
|
|
|||
|
|
def reset(self):
|
|||
|
|
self.mat.zero_()
|
|||
|
|
|
|||
|
|
def compute(self):
|
|||
|
|
h = self.mat.float()
|
|||
|
|
acc_global = torch.diag(h).sum() / h.sum()
|
|||
|
|
acc = torch.diag(h) / h.sum(1)
|
|||
|
|
iu = torch.diag(h) / (h.sum(1) + h.sum(0) - torch.diag(h))
|
|||
|
|
return acc_global, acc, iu
|
|||
|
|
|
|||
|
|
def reduce_from_all_processes(self):
|
|||
|
|
reduce_across_processes(self.mat)
|
|||
|
|
|
|||
|
|
def get_info(self):
|
|||
|
|
acc_global, acc, iu = self.compute()
|
|||
|
|
return ("global correct: {:.1f}\naverage row correct: {}\nIoU: {}\nmean IoU: {:.1f}").format(
|
|||
|
|
acc_global.item() * 100,
|
|||
|
|
[f"{i:.1f}" for i in (acc * 100).tolist()],
|
|||
|
|
[f"{i:.1f}" for i in (iu * 100).tolist()],
|
|||
|
|
iu.mean().item() * 100,
|
|||
|
|
), iu.mean().item() * 100
|
|||
|
|
|
|||
|
|
|
|||
|
|
class MetricLogger:
|
|||
|
|
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()
|
|||
|
|
if not isinstance(v, (float, int)):
|
|||
|
|
raise TypeError(
|
|||
|
|
f"This method expects the value of the input arguments to be of type float or int, instead got {type(v)}"
|
|||
|
|
)
|
|||
|
|
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(
|
|||
|
|
f"'{type(self).__name__}' object has no attribute '{attr}'")
|
|||
|
|
|
|||
|
|
def __str__(self):
|
|||
|
|
loss_str = []
|
|||
|
|
for name, meter in self.meters.items():
|
|||
|
|
loss_str.append(f"{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:
|
|||
|
|
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(f"{header} Total time: {total_time_str}")
|
|||
|
|
|
|||
|
|
|
|||
|
|
def cat_list(images, fill_value=0):
|
|||
|
|
max_size = tuple(max(s) for s in zip(*[img.shape for img in images]))
|
|||
|
|
batch_shape = (len(images),) + max_size
|
|||
|
|
batched_imgs = images[0].new(*batch_shape).fill_(fill_value)
|
|||
|
|
for img, pad_img in zip(images, batched_imgs):
|
|||
|
|
pad_img[..., : img.shape[-2], : img.shape[-1]].copy_(img)
|
|||
|
|
return batched_imgs
|
|||
|
|
|
|||
|
|
|
|||
|
|
def collate_fn(batch):
|
|||
|
|
images, targets = list(zip(*batch))
|
|||
|
|
batched_imgs = cat_list(images, fill_value=0)
|
|||
|
|
batched_targets = cat_list(targets, fill_value=255)
|
|||
|
|
return batched_imgs, batched_targets
|
|||
|
|
|
|||
|
|
|
|||
|
|
def mkdir(path):
|
|||
|
|
try:
|
|||
|
|
os.makedirs(path)
|
|||
|
|
except OSError as e:
|
|||
|
|
if e.errno != errno.EEXIST:
|
|||
|
|
raise
|
|||
|
|
|
|||
|
|
|
|||
|
|
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()
|
|||
|
|
elif hasattr(args, "rank"):
|
|||
|
|
pass
|
|||
|
|
else:
|
|||
|
|
print("Not using distributed mode")
|
|||
|
|
args.distributed = False
|
|||
|
|
return
|
|||
|
|
|
|||
|
|
args.distributed = True
|
|||
|
|
|
|||
|
|
torch.cuda.set_device(args.gpu)
|
|||
|
|
args.dist_backend = "nccl"
|
|||
|
|
print(
|
|||
|
|
f"| distributed init (rank {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)
|
|||
|
|
|
|||
|
|
|
|||
|
|
def reduce_across_processes(val):
|
|||
|
|
if not is_dist_avail_and_initialized():
|
|||
|
|
# nothing to sync, but we still convert to tensor for consistency with the distributed case.
|
|||
|
|
return torch.tensor(val)
|
|||
|
|
|
|||
|
|
t = torch.tensor(val, device="cuda")
|
|||
|
|
dist.barrier()
|
|||
|
|
dist.all_reduce(t)
|
|||
|
|
return t
|
|||
|
|
|
|||
|
|
|
|||
|
|
def create_lr_scheduler(optimizer,
|
|||
|
|
num_step: int,
|
|||
|
|
epochs: int,
|
|||
|
|
warmup=True,
|
|||
|
|
warmup_epochs=1,
|
|||
|
|
warmup_factor=1e-3):
|
|||
|
|
assert num_step > 0 and epochs > 0
|
|||
|
|
if warmup is False:
|
|||
|
|
warmup_epochs = 0
|
|||
|
|
|
|||
|
|
def f(x):
|
|||
|
|
"""
|
|||
|
|
根据step数返回一个学习率倍率因子，
|
|||
|
|
注意在训练开始之前，pytorch会提前调用一次lr_scheduler.step()方法
|
|||
|
|
"""
|
|||
|
|
if warmup is True and x <= (warmup_epochs * num_step):
|
|||
|
|
alpha = float(x) / (warmup_epochs * num_step)
|
|||
|
|
# warmup过程中lr倍率因子从warmup_factor -> 1
|
|||
|
|
return warmup_factor * (1 - alpha) + alpha
|
|||
|
|
else:
|
|||
|
|
# warmup后lr倍率因子从1 -> 0
|
|||
|
|
# 参考deeplab_v2: Learning rate policy
|
|||
|
|
return (1 - (x - warmup_epochs * num_step) / ((epochs - warmup_epochs) * num_step)) ** 0.9
|
|||
|
|
|
|||
|
|
return torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=f)
|