|
|
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 __str__(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, |
|
|
) |
|
|
|
|
|
|
|
|
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(): |
|
|
|
|
|
return torch.tensor(val) |
|
|
|
|
|
t = torch.tensor(val, device="cuda") if isinstance(val, int) else val.clone().detach().to("cuda") |
|
|
dist.barrier() |
|
|
dist.all_reduce(t) |
|
|
return t |
|
|
|
