File size: 17,832 Bytes
938e515
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
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
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
# Copyright (c) Facebook, Inc. and its affiliates.
# ------------------------------------------------------------------------------
# Copyright (c) Microsoft
# Licensed under the MIT License.
# Written by Bin Xiao (leoxiaobin@gmail.com)
# Modified by Bowen Cheng (bcheng9@illinois.edu)
# Adapted from https://github.com/HRNet/Higher-HRNet-Human-Pose-Estimation/blob/master/lib/models/pose_higher_hrnet.py  # noqa
# ------------------------------------------------------------------------------

from __future__ import absolute_import, division, print_function
import logging
import torch.nn as nn

from detectron2.layers import ShapeSpec
from detectron2.modeling.backbone import BACKBONE_REGISTRY
from detectron2.modeling.backbone.backbone import Backbone

BN_MOMENTUM = 0.1
logger = logging.getLogger(__name__)

__all__ = ["build_pose_hrnet_backbone", "PoseHigherResolutionNet"]


def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False)


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.conv3 = nn.Conv2d(planes, planes * self.expansion, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * self.expansion, momentum=BN_MOMENTUM)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)

        out = self.conv3(out)
        out = self.bn3(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class HighResolutionModule(nn.Module):
    """HighResolutionModule
    Building block of the PoseHigherResolutionNet (see lower)
    arXiv: https://arxiv.org/abs/1908.10357
    Args:
        num_branches (int): number of branches of the modyle
        blocks (str): type of block of the module
        num_blocks (int): number of blocks of the module
        num_inchannels (int): number of input channels of the module
        num_channels (list): number of channels of each branch
        multi_scale_output (bool): only used by the last module of PoseHigherResolutionNet
    """

    def __init__(
        self,
        num_branches,
        blocks,
        num_blocks,
        num_inchannels,
        num_channels,
        multi_scale_output=True,
    ):
        super(HighResolutionModule, self).__init__()
        self._check_branches(num_branches, blocks, num_blocks, num_inchannels, num_channels)

        self.num_inchannels = num_inchannels
        self.num_branches = num_branches

        self.multi_scale_output = multi_scale_output

        self.branches = self._make_branches(num_branches, blocks, num_blocks, num_channels)
        self.fuse_layers = self._make_fuse_layers()
        self.relu = nn.ReLU(True)

    def _check_branches(self, num_branches, blocks, num_blocks, num_inchannels, num_channels):
        if num_branches != len(num_blocks):
            error_msg = "NUM_BRANCHES({}) <> NUM_BLOCKS({})".format(num_branches, len(num_blocks))
            logger.error(error_msg)
            raise ValueError(error_msg)

        if num_branches != len(num_channels):
            error_msg = "NUM_BRANCHES({}) <> NUM_CHANNELS({})".format(
                num_branches, len(num_channels)
            )
            logger.error(error_msg)
            raise ValueError(error_msg)

        if num_branches != len(num_inchannels):
            error_msg = "NUM_BRANCHES({}) <> NUM_INCHANNELS({})".format(
                num_branches, len(num_inchannels)
            )
            logger.error(error_msg)
            raise ValueError(error_msg)

    def _make_one_branch(self, branch_index, block, num_blocks, num_channels, stride=1):
        downsample = None
        if (
            stride != 1
            or self.num_inchannels[branch_index] != num_channels[branch_index] * block.expansion
        ):
            downsample = nn.Sequential(
                nn.Conv2d(
                    self.num_inchannels[branch_index],
                    num_channels[branch_index] * block.expansion,
                    kernel_size=1,
                    stride=stride,
                    bias=False,
                ),
                nn.BatchNorm2d(num_channels[branch_index] * block.expansion, momentum=BN_MOMENTUM),
            )

        layers = []
        layers.append(
            block(self.num_inchannels[branch_index], num_channels[branch_index], stride, downsample)
        )
        self.num_inchannels[branch_index] = num_channels[branch_index] * block.expansion
        for _ in range(1, num_blocks[branch_index]):
            layers.append(block(self.num_inchannels[branch_index], num_channels[branch_index]))

        return nn.Sequential(*layers)

    def _make_branches(self, num_branches, block, num_blocks, num_channels):
        branches = []

        for i in range(num_branches):
            branches.append(self._make_one_branch(i, block, num_blocks, num_channels))

        return nn.ModuleList(branches)

    def _make_fuse_layers(self):
        if self.num_branches == 1:
            return None

        num_branches = self.num_branches
        num_inchannels = self.num_inchannels
        fuse_layers = []
        for i in range(num_branches if self.multi_scale_output else 1):
            fuse_layer = []
            for j in range(num_branches):
                if j > i:
                    fuse_layer.append(
                        nn.Sequential(
                            nn.Conv2d(num_inchannels[j], num_inchannels[i], 1, 1, 0, bias=False),
                            nn.BatchNorm2d(num_inchannels[i]),
                            nn.Upsample(scale_factor=2 ** (j - i), mode="nearest"),
                        )
                    )
                elif j == i:
                    fuse_layer.append(None)
                else:
                    conv3x3s = []
                    for k in range(i - j):
                        if k == i - j - 1:
                            num_outchannels_conv3x3 = num_inchannels[i]
                            conv3x3s.append(
                                nn.Sequential(
                                    nn.Conv2d(
                                        num_inchannels[j],
                                        num_outchannels_conv3x3,
                                        3,
                                        2,
                                        1,
                                        bias=False,
                                    ),
                                    nn.BatchNorm2d(num_outchannels_conv3x3),
                                )
                            )
                        else:
                            num_outchannels_conv3x3 = num_inchannels[j]
                            conv3x3s.append(
                                nn.Sequential(
                                    nn.Conv2d(
                                        num_inchannels[j],
                                        num_outchannels_conv3x3,
                                        3,
                                        2,
                                        1,
                                        bias=False,
                                    ),
                                    nn.BatchNorm2d(num_outchannels_conv3x3),
                                    nn.ReLU(True),
                                )
                            )
                    fuse_layer.append(nn.Sequential(*conv3x3s))
            fuse_layers.append(nn.ModuleList(fuse_layer))

        return nn.ModuleList(fuse_layers)

    def get_num_inchannels(self):
        return self.num_inchannels

    def forward(self, x):
        if self.num_branches == 1:
            return [self.branches[0](x[0])]

        for i in range(self.num_branches):
            x[i] = self.branches[i](x[i])

        x_fuse = []

        for i in range(len(self.fuse_layers)):
            y = x[0] if i == 0 else self.fuse_layers[i][0](x[0])
            for j in range(1, self.num_branches):
                if i == j:
                    y = y + x[j]
                else:
                    z = self.fuse_layers[i][j](x[j])[:, :, : y.shape[2], : y.shape[3]]
                    y = y + z
            x_fuse.append(self.relu(y))

        return x_fuse


blocks_dict = {"BASIC": BasicBlock, "BOTTLENECK": Bottleneck}


class PoseHigherResolutionNet(Backbone):
    """PoseHigherResolutionNet
    Composed of several HighResolutionModule tied together with ConvNets
    Adapted from the GitHub version to fit with HRFPN and the Detectron2 infrastructure
    arXiv: https://arxiv.org/abs/1908.10357
    """

    def __init__(self, cfg, **kwargs):
        self.inplanes = cfg.MODEL.HRNET.STEM_INPLANES
        super(PoseHigherResolutionNet, self).__init__()

        # stem net
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=2, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64, momentum=BN_MOMENTUM)
        self.conv2 = nn.Conv2d(64, 64, kernel_size=3, stride=2, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(64, momentum=BN_MOMENTUM)
        self.relu = nn.ReLU(inplace=True)
        self.layer1 = self._make_layer(Bottleneck, 64, 4)

        self.stage2_cfg = cfg.MODEL.HRNET.STAGE2
        num_channels = self.stage2_cfg.NUM_CHANNELS
        block = blocks_dict[self.stage2_cfg.BLOCK]
        num_channels = [num_channels[i] * block.expansion for i in range(len(num_channels))]
        self.transition1 = self._make_transition_layer([256], num_channels)
        self.stage2, pre_stage_channels = self._make_stage(self.stage2_cfg, num_channels)

        self.stage3_cfg = cfg.MODEL.HRNET.STAGE3
        num_channels = self.stage3_cfg.NUM_CHANNELS
        block = blocks_dict[self.stage3_cfg.BLOCK]
        num_channels = [num_channels[i] * block.expansion for i in range(len(num_channels))]
        self.transition2 = self._make_transition_layer(pre_stage_channels, num_channels)
        self.stage3, pre_stage_channels = self._make_stage(self.stage3_cfg, num_channels)

        self.stage4_cfg = cfg.MODEL.HRNET.STAGE4
        num_channels = self.stage4_cfg.NUM_CHANNELS
        block = blocks_dict[self.stage4_cfg.BLOCK]
        num_channels = [num_channels[i] * block.expansion for i in range(len(num_channels))]
        self.transition3 = self._make_transition_layer(pre_stage_channels, num_channels)
        self.stage4, pre_stage_channels = self._make_stage(
            self.stage4_cfg, num_channels, multi_scale_output=True
        )

        self._out_features = []
        self._out_feature_channels = {}
        self._out_feature_strides = {}

        for i in range(cfg.MODEL.HRNET.STAGE4.NUM_BRANCHES):
            self._out_features.append("p%d" % (i + 1))
            self._out_feature_channels.update(
                {self._out_features[-1]: cfg.MODEL.HRNET.STAGE4.NUM_CHANNELS[i]}
            )
            self._out_feature_strides.update({self._out_features[-1]: 1})

    def _get_deconv_cfg(self, deconv_kernel):
        if deconv_kernel == 4:
            padding = 1
            output_padding = 0
        elif deconv_kernel == 3:
            padding = 1
            output_padding = 1
        elif deconv_kernel == 2:
            padding = 0
            output_padding = 0

        return deconv_kernel, padding, output_padding

    def _make_transition_layer(self, num_channels_pre_layer, num_channels_cur_layer):
        num_branches_cur = len(num_channels_cur_layer)
        num_branches_pre = len(num_channels_pre_layer)

        transition_layers = []
        for i in range(num_branches_cur):
            if i < num_branches_pre:
                if num_channels_cur_layer[i] != num_channels_pre_layer[i]:
                    transition_layers.append(
                        nn.Sequential(
                            nn.Conv2d(
                                num_channels_pre_layer[i],
                                num_channels_cur_layer[i],
                                3,
                                1,
                                1,
                                bias=False,
                            ),
                            nn.BatchNorm2d(num_channels_cur_layer[i]),
                            nn.ReLU(inplace=True),
                        )
                    )
                else:
                    transition_layers.append(None)
            else:
                conv3x3s = []
                for j in range(i + 1 - num_branches_pre):
                    inchannels = num_channels_pre_layer[-1]
                    outchannels = (
                        num_channels_cur_layer[i] if j == i - num_branches_pre else inchannels
                    )
                    conv3x3s.append(
                        nn.Sequential(
                            nn.Conv2d(inchannels, outchannels, 3, 2, 1, bias=False),
                            nn.BatchNorm2d(outchannels),
                            nn.ReLU(inplace=True),
                        )
                    )
                transition_layers.append(nn.Sequential(*conv3x3s))

        return nn.ModuleList(transition_layers)

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(
                    self.inplanes,
                    planes * block.expansion,
                    kernel_size=1,
                    stride=stride,
                    bias=False,
                ),
                nn.BatchNorm2d(planes * block.expansion, momentum=BN_MOMENTUM),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for _ in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        return nn.Sequential(*layers)

    def _make_stage(self, layer_config, num_inchannels, multi_scale_output=True):
        num_modules = layer_config["NUM_MODULES"]
        num_branches = layer_config["NUM_BRANCHES"]
        num_blocks = layer_config["NUM_BLOCKS"]
        num_channels = layer_config["NUM_CHANNELS"]
        block = blocks_dict[layer_config["BLOCK"]]

        modules = []
        for i in range(num_modules):
            # multi_scale_output is only used last module
            if not multi_scale_output and i == num_modules - 1:
                reset_multi_scale_output = False
            else:
                reset_multi_scale_output = True

            modules.append(
                HighResolutionModule(
                    num_branches,
                    block,
                    num_blocks,
                    num_inchannels,
                    num_channels,
                    reset_multi_scale_output,
                )
            )
            num_inchannels = modules[-1].get_num_inchannels()

        return nn.Sequential(*modules), num_inchannels

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.conv2(x)
        x = self.bn2(x)
        x = self.relu(x)
        x = self.layer1(x)

        x_list = []
        for i in range(self.stage2_cfg.NUM_BRANCHES):
            if self.transition1[i] is not None:
                x_list.append(self.transition1[i](x))
            else:
                x_list.append(x)
        y_list = self.stage2(x_list)

        x_list = []
        for i in range(self.stage3_cfg.NUM_BRANCHES):
            if self.transition2[i] is not None:
                x_list.append(self.transition2[i](y_list[-1]))
            else:
                x_list.append(y_list[i])
        y_list = self.stage3(x_list)

        x_list = []
        for i in range(self.stage4_cfg.NUM_BRANCHES):
            if self.transition3[i] is not None:
                x_list.append(self.transition3[i](y_list[-1]))
            else:
                x_list.append(y_list[i])
        y_list = self.stage4(x_list)

        assert len(self._out_features) == len(y_list)
        return dict(zip(self._out_features, y_list))  # final_outputs


@BACKBONE_REGISTRY.register()
def build_pose_hrnet_backbone(cfg, input_shape: ShapeSpec):
    model = PoseHigherResolutionNet(cfg)
    return model