154 lines
4.9 KiB
Python
154 lines
4.9 KiB
Python
import datetime
|
|
import time
|
|
from collections import defaultdict, deque
|
|
|
|
import torch
|
|
|
|
from .distributed import reduce_across_processes
|
|
|
|
|
|
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="{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 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, **kwargs):
|
|
self.meters[name] = SmoothedValue(**kwargs)
|
|
|
|
def log_every(self, iterable, print_freq=5, 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 print_freq is not None and 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}")
|