utils.py 8.73 KB
Newer Older
1
import datetime
2
3
import errno
import os
4
import time
5
6
from collections import defaultdict, deque

7
8
9
10
import torch
import torch.distributed as dist


11
class SmoothedValue:
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
    """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
35
        t = torch.tensor([self.count, self.total], dtype=torch.float64, device="cuda")
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
        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(
66
67
            median=self.median, avg=self.avg, global_avg=self.global_avg, max=self.max, value=self.value
        )
68
69


70
class ConfusionMatrix:
71
72
73
74
75
76
77
78
    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)
79
        with torch.inference_mode():
80
81
            k = (a >= 0) & (a < n)
            inds = n * a[k].to(torch.int64) + b[k]
82
            self.mat += torch.bincount(inds, minlength=n ** 2).reshape(n, n)
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103

    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):
        if not torch.distributed.is_available():
            return
        if not torch.distributed.is_initialized():
            return
        torch.distributed.barrier()
        torch.distributed.all_reduce(self.mat)

    def __str__(self):
        acc_global, acc, iu = self.compute()
104
        return ("global correct: {:.1f}\naverage row correct: {}\nIoU: {}\nmean IoU: {:.1f}").format(
105
            acc_global.item() * 100,
106
107
            [f"{i:.1f}" for i in (acc * 100).tolist()],
            [f"{i:.1f}" for i in (iu * 100).tolist()],
108
109
            iu.mean().item() * 100,
        )
110
111


112
class MetricLogger:
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
    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]
129
        raise AttributeError(f"'{type(self).__name__}' object has no attribute '{attr}'")
130
131
132
133

    def __str__(self):
        loss_str = []
        for name, meter in self.meters.items():
134
            loss_str.append(f"{name}: {str(meter)}")
135
136
137
138
139
140
141
142
143
144
145
146
        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:
147
            header = ""
148
149
        start_time = time.time()
        end = time.time()
150
151
152
        iter_time = SmoothedValue(fmt="{avg:.4f}")
        data_time = SmoothedValue(fmt="{avg:.4f}")
        space_fmt = ":" + str(len(str(len(iterable)))) + "d"
153
        if torch.cuda.is_available():
154
155
156
157
158
159
160
161
162
163
164
            log_msg = self.delimiter.join(
                [
                    header,
                    "[{0" + space_fmt + "}/{1}]",
                    "eta: {eta}",
                    "{meters}",
                    "time: {time}",
                    "data: {data}",
                    "max mem: {memory:.0f}",
                ]
            )
165
        else:
166
167
168
            log_msg = self.delimiter.join(
                [header, "[{0" + space_fmt + "}/{1}]", "eta: {eta}", "{meters}", "time: {time}", "data: {data}"]
            )
169
170
171
172
173
174
175
176
        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)))
177
                if torch.cuda.is_available():
178
179
180
181
182
183
184
185
186
187
188
                    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,
                        )
                    )
189
                else:
190
191
192
193
194
                    print(
                        log_msg.format(
                            i, len(iterable), eta=eta_string, meters=str(self), time=str(iter_time), data=str(data_time)
                        )
                    )
195
196
197
198
            i += 1
            end = time.time()
        total_time = time.time() - start_time
        total_time_str = str(datetime.timedelta(seconds=int(total_time)))
199
        print(f"{header} Total time: {total_time_str}")
200
201
202
203
204
205
206


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):
207
        pad_img[..., : img.shape[-2], : img.shape[-1]].copy_(img)
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
    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__
231

232
233
234
    builtin_print = __builtin__.print

    def print(*args, **kwargs):
235
        force = kwargs.pop("force", False)
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
        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):
272
    if "RANK" in os.environ and "WORLD_SIZE" in os.environ:
273
        args.rank = int(os.environ["RANK"])
274
275
276
277
        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"])
278
279
280
281
        args.gpu = args.rank % torch.cuda.device_count()
    elif hasattr(args, "rank"):
        pass
    else:
282
        print("Not using distributed mode")
283
284
285
286
287
288
        args.distributed = False
        return

    args.distributed = True

    torch.cuda.set_device(args.gpu)
289
    args.dist_backend = "nccl"
290
    print(f"| distributed init (rank {args.rank}): {args.dist_url}", flush=True)
291
292
293
    torch.distributed.init_process_group(
        backend=args.dist_backend, init_method=args.dist_url, world_size=args.world_size, rank=args.rank
    )
294
    setup_for_distributed(args.rank == 0)