File size: 14,798 Bytes
f53b39e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright (C) 2022-present Naver Corporation. All rights reserved.
# Licensed under CC BY-NC-SA 4.0 (non-commercial use only).

# --------------------------------------------------------
# DPT head for ViTs
# --------------------------------------------------------
# References: 
# https://github.com/isl-org/DPT
# https://github.com/EPFL-VILAB/MultiMAE/blob/main/multimae/output_adapters.py

import torch
import torch.nn as nn
import torch.nn.functional as F
from einops import rearrange, repeat
from typing import Union, Tuple, Iterable, List, Optional, Dict

def pair(t):
    return t if isinstance(t, tuple) else (t, t)

def make_scratch(in_shape, out_shape, groups=1, expand=False):
    scratch = nn.Module()

    out_shape1 = out_shape
    out_shape2 = out_shape
    out_shape3 = out_shape
    out_shape4 = out_shape
    if expand == True:
        out_shape1 = out_shape
        out_shape2 = out_shape * 2
        out_shape3 = out_shape * 4
        out_shape4 = out_shape * 8

    scratch.layer1_rn = nn.Conv2d(
        in_shape[0],
        out_shape1,
        kernel_size=3,
        stride=1,
        padding=1,
        bias=False,
        groups=groups,
    )
    scratch.layer2_rn = nn.Conv2d(
        in_shape[1],
        out_shape2,
        kernel_size=3,
        stride=1,
        padding=1,
        bias=False,
        groups=groups,
    )
    scratch.layer3_rn = nn.Conv2d(
        in_shape[2],
        out_shape3,
        kernel_size=3,
        stride=1,
        padding=1,
        bias=False,
        groups=groups,
    )
    scratch.layer4_rn = nn.Conv2d(
        in_shape[3],
        out_shape4,
        kernel_size=3,
        stride=1,
        padding=1,
        bias=False,
        groups=groups,
    )

    scratch.layer_rn = nn.ModuleList([
        scratch.layer1_rn,
        scratch.layer2_rn,
        scratch.layer3_rn,
        scratch.layer4_rn,
    ])

    return scratch

class ResidualConvUnit_custom(nn.Module):
    """Residual convolution module."""

    def __init__(self, features, activation, bn):
        """Init.
        Args:
            features (int): number of features
        """
        super().__init__()

        self.bn = bn

        self.groups = 1

        self.conv1 = nn.Conv2d(
            features,
            features,
            kernel_size=3,
            stride=1,
            padding=1,
            bias=not self.bn,
            groups=self.groups,
        )

        self.conv2 = nn.Conv2d(
            features,
            features,
            kernel_size=3,
            stride=1,
            padding=1,
            bias=not self.bn,
            groups=self.groups,
        )

        if self.bn == True:
            self.bn1 = nn.BatchNorm2d(features)
            self.bn2 = nn.BatchNorm2d(features)

        self.activation = activation

        self.skip_add = nn.quantized.FloatFunctional()

    def forward(self, x):
        """Forward pass.
        Args:
            x (tensor): input
        Returns:
            tensor: output
        """

        out = self.activation(x)
        out = self.conv1(out)
        if self.bn == True:
            out = self.bn1(out)

        out = self.activation(out)
        out = self.conv2(out)
        if self.bn == True:
            out = self.bn2(out)

        if self.groups > 1:
            out = self.conv_merge(out)

        return self.skip_add.add(out, x)

class FeatureFusionBlock_custom(nn.Module):
    """Feature fusion block."""

    def __init__(
        self,
        features,
        activation,
        deconv=False,
        bn=False,
        expand=False,
        align_corners=True,
        width_ratio=1,
    ):
        """Init.
        Args:
            features (int): number of features
        """
        super(FeatureFusionBlock_custom, self).__init__()
        self.width_ratio = width_ratio

        self.deconv = deconv
        self.align_corners = align_corners

        self.groups = 1

        self.expand = expand
        out_features = features
        if self.expand == True:
            out_features = features // 2

        self.out_conv = nn.Conv2d(
            features,
            out_features,
            kernel_size=1,
            stride=1,
            padding=0,
            bias=True,
            groups=1,
        )

        self.resConfUnit1 = ResidualConvUnit_custom(features, activation, bn)
        self.resConfUnit2 = ResidualConvUnit_custom(features, activation, bn)

        self.skip_add = nn.quantized.FloatFunctional()

    def forward(self, *xs):
        """Forward pass.
        Returns:
            tensor: output
        """
        output = xs[0]

        if len(xs) == 2:
            res = self.resConfUnit1(xs[1])
            if self.width_ratio != 1:
                res = F.interpolate(res, size=(output.shape[2], output.shape[3]), mode='bilinear')

            output = self.skip_add.add(output, res)
            # output += res

        output = self.resConfUnit2(output)

        if self.width_ratio != 1:
            # and output.shape[3] < self.width_ratio * output.shape[2]
            #size=(image.shape[])
            if (output.shape[3] / output.shape[2]) < (2 / 3) * self.width_ratio:
                shape = 3 * output.shape[3]
            else:
                shape = int(self.width_ratio * 2 * output.shape[2])
            output  = F.interpolate(output, size=(2* output.shape[2], shape), mode='bilinear')
        else:
            output = nn.functional.interpolate(output, scale_factor=2,
                    mode="bilinear", align_corners=self.align_corners)
        output = self.out_conv(output)
        return output

def make_fusion_block(features, use_bn, width_ratio=1):
    return FeatureFusionBlock_custom(
        features,
        nn.ReLU(False),
        deconv=False,
        bn=use_bn,
        expand=False,
        align_corners=True,
        width_ratio=width_ratio,
    )

class Interpolate(nn.Module):
    """Interpolation module."""

    def __init__(self, scale_factor, mode, align_corners=False):
        """Init.
        Args:
            scale_factor (float): scaling
            mode (str): interpolation mode
        """
        super(Interpolate, self).__init__()

        self.interp = nn.functional.interpolate
        self.scale_factor = scale_factor
        self.mode = mode
        self.align_corners = align_corners

    def forward(self, x):
        """Forward pass.
        Args:
            x (tensor): input
        Returns:
            tensor: interpolated data
        """

        x = self.interp(
            x,
            scale_factor=self.scale_factor,
            mode=self.mode,
            align_corners=self.align_corners,
        )

        return x

class DPTOutputAdapter(nn.Module):
    """DPT output adapter.

    :param num_cahnnels: Number of output channels
    :param stride_level: tride level compared to the full-sized image.
        E.g. 4 for 1/4th the size of the image.
    :param patch_size_full: Int or tuple of the patch size over the full image size.
        Patch size for smaller inputs will be computed accordingly.
    :param hooks: Index of intermediate layers
    :param layer_dims: Dimension of intermediate layers
    :param feature_dim: Feature dimension
    :param last_dim: out_channels/in_channels for the last two Conv2d when head_type == regression
    :param use_bn: If set to True, activates batch norm
    :param dim_tokens_enc:  Dimension of tokens coming from encoder
    """

    def __init__(self,
                 num_channels: int = 1,
                 stride_level: int = 1,
                 patch_size: Union[int, Tuple[int, int]] = 16,
                 main_tasks: Iterable[str] = ('rgb',),
                 hooks: List[int] = [2, 5, 8, 11],
                 layer_dims: List[int] = [96, 192, 384, 768],
                 feature_dim: int = 256,
                 last_dim: int = 32,
                 use_bn: bool = False,
                 dim_tokens_enc: Optional[int] = None,
                 head_type: str = 'regression',
                 output_width_ratio=1,
                 **kwargs):
        super().__init__()
        self.num_channels = num_channels
        self.stride_level = stride_level
        self.patch_size = pair(patch_size)
        self.main_tasks = main_tasks
        self.hooks = hooks
        self.layer_dims = layer_dims
        self.feature_dim = feature_dim
        self.dim_tokens_enc = dim_tokens_enc * len(self.main_tasks) if dim_tokens_enc is not None else None
        self.head_type = head_type

        # Actual patch height and width, taking into account stride of input
        self.P_H = max(1, self.patch_size[0] // stride_level)
        self.P_W = max(1, self.patch_size[1] // stride_level)

        self.scratch = make_scratch(layer_dims, feature_dim, groups=1, expand=False)

        self.scratch.refinenet1 = make_fusion_block(feature_dim, use_bn, output_width_ratio)
        self.scratch.refinenet2 = make_fusion_block(feature_dim, use_bn, output_width_ratio)
        self.scratch.refinenet3 = make_fusion_block(feature_dim, use_bn, output_width_ratio)
        self.scratch.refinenet4 = make_fusion_block(feature_dim, use_bn, output_width_ratio)
        # self.mask_head = nn.Sequential(
        #         nn.Conv2d(feature_dim, feature_dim, kernel_size=3, padding=1, bias=False),
        #         nn.BatchNorm2d(feature_dim) if use_bn else nn.Identity(),
        #         nn.ReLU(True),
        #         nn.Dropout(0.1, False),
        #         nn.Conv2d(feature_dim, 1, kernel_size=1),
        #         Interpolate(scale_factor=2, mode="bilinear", align_corners=True),
        #     )
        if self.head_type == 'regression':
            # The "DPTDepthModel" head
            self.head = nn.Sequential(
                nn.Conv2d(feature_dim, feature_dim // 2, kernel_size=3, stride=1, padding=1),
                Interpolate(scale_factor=2, mode="bilinear", align_corners=True),
                nn.Conv2d(feature_dim // 2, last_dim, kernel_size=3, stride=1, padding=1),
                nn.ReLU(True),
                nn.Conv2d(last_dim, self.num_channels, kernel_size=1, stride=1, padding=0)
            )
        elif self.head_type == 'semseg':
            # The "DPTSegmentationModel" head
            self.head = nn.Sequential(
                nn.Conv2d(feature_dim, feature_dim, kernel_size=3, padding=1, bias=False),
                nn.BatchNorm2d(feature_dim) if use_bn else nn.Identity(),
                nn.ReLU(True),
                nn.Dropout(0.1, False),
                nn.Conv2d(feature_dim, self.num_channels, kernel_size=1),
                Interpolate(scale_factor=2, mode="bilinear", align_corners=True),
            )
        else:
            raise ValueError('DPT head_type must be "regression" or "semseg".')

        if self.dim_tokens_enc is not None:
            self.init(dim_tokens_enc=dim_tokens_enc)

    def init(self, dim_tokens_enc=768):
        """
        Initialize parts of decoder that are dependent on dimension of encoder tokens.
        Should be called when setting up MultiMAE.

        :param dim_tokens_enc: Dimension of tokens coming from encoder
        """
        #print(dim_tokens_enc)

        # Set up activation postprocessing layers
        if isinstance(dim_tokens_enc, int):
            dim_tokens_enc = 4 * [dim_tokens_enc]

        self.dim_tokens_enc = [dt * len(self.main_tasks) for dt in dim_tokens_enc]

        self.act_1_postprocess = nn.Sequential(
            nn.Conv2d(
                in_channels=self.dim_tokens_enc[0],
                out_channels=self.layer_dims[0],
                kernel_size=1, stride=1, padding=0,
            ),
            nn.ConvTranspose2d(
                in_channels=self.layer_dims[0],
                out_channels=self.layer_dims[0],
                kernel_size=4, stride=4, padding=0,
                bias=True, dilation=1, groups=1,
            )
        )

        self.act_2_postprocess = nn.Sequential(
            nn.Conv2d(
                in_channels=self.dim_tokens_enc[1],
                out_channels=self.layer_dims[1],
                kernel_size=1, stride=1, padding=0,
            ),
            nn.ConvTranspose2d(
                in_channels=self.layer_dims[1],
                out_channels=self.layer_dims[1],
                kernel_size=2, stride=2, padding=0,
                bias=True, dilation=1, groups=1,
            )
        )

        self.act_3_postprocess = nn.Sequential(
            nn.Conv2d(
                in_channels=self.dim_tokens_enc[2],
                out_channels=self.layer_dims[2],
                kernel_size=1, stride=1, padding=0,
            )
        )

        self.act_4_postprocess = nn.Sequential(
            nn.Conv2d(
                in_channels=self.dim_tokens_enc[3],
                out_channels=self.layer_dims[3],
                kernel_size=1, stride=1, padding=0,
            ),
            nn.Conv2d(
                in_channels=self.layer_dims[3],
                out_channels=self.layer_dims[3],
                kernel_size=3, stride=2, padding=1,
            )
        )

        self.act_postprocess = nn.ModuleList([
            self.act_1_postprocess,
            self.act_2_postprocess,
            self.act_3_postprocess,
            self.act_4_postprocess
        ])

    def adapt_tokens(self, encoder_tokens):
        # Adapt tokens
        x = []
        x.append(encoder_tokens[:, :])
        x = torch.cat(x, dim=-1)
        return x

    def forward(self, encoder_tokens: List[torch.Tensor], image_size):
            #input_info: Dict):
        assert self.dim_tokens_enc is not None, 'Need to call init(dim_tokens_enc) function first'
        H, W = image_size
        
        # Number of patches in height and width
        N_H = H // (self.stride_level * self.P_H)
        N_W = W // (self.stride_level * self.P_W)

        # Hook decoder onto 4 layers from specified ViT layers
        layers = [encoder_tokens[hook] for hook in self.hooks]

        # Extract only task-relevant tokens and ignore global tokens.
        layers = [self.adapt_tokens(l) for l in layers]

        # Reshape tokens to spatial representation
        layers = [rearrange(l, 'b (nh nw) c -> b c nh nw', nh=N_H, nw=N_W) for l in layers]

        layers = [self.act_postprocess[idx](l) for idx, l in enumerate(layers)]
        # Project layers to chosen feature dim
        layers = [self.scratch.layer_rn[idx](l) for idx, l in enumerate(layers)]

        # Fuse layers using refinement stages
        path_4 = self.scratch.refinenet4(layers[3])
        path_3 = self.scratch.refinenet3(path_4, layers[2])
        path_2 = self.scratch.refinenet2(path_3, layers[1])
        path_1 = self.scratch.refinenet1(path_2, layers[0])

        # Output head
        out = self.head(path_1)
        
        return out