File size: 19,426 Bytes
ab854b9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Ultralytics YOLO 🚀, AGPL-3.0 license
"""
Model head modules
"""

import math

import torch
import torch.nn as nn
from torch.nn.init import constant_, xavier_uniform_

from ultralytics.utils.tal import TORCH_1_10, dist2bbox, make_anchors

from .block import DFL, Proto
from .conv import Conv
from .transformer import MLP, DeformableTransformerDecoder, DeformableTransformerDecoderLayer
from .utils import bias_init_with_prob, linear_init_

__all__ = 'Detect', 'Segment','ExtendedSegment' ,'Pose', 'Classify', 'RTDETRDecoder'


class Detect(nn.Module):
    """YOLOv8 Detect head for detection models."""
    dynamic = False  # force grid reconstruction
    export = False  # export mode
    shape = None
    anchors = torch.empty(0)  # init
    strides = torch.empty(0)  # init

    def __init__(self, nc=80, ch=()):  # detection layer
        super().__init__()
        self.nc = nc  # number of classes
        self.nl = len(ch)  # number of detection layers
        self.reg_max = 16  # DFL channels (ch[0] // 16 to scale 4/8/12/16/20 for n/s/m/l/x)
        self.no = nc + self.reg_max * 4  # number of outputs per anchor
        self.stride = torch.zeros(self.nl)  # strides computed during build
        c2, c3 = max((16, ch[0] // 4, self.reg_max * 4)), max(ch[0], min(self.nc, 100))  # channels
        self.cv2 = nn.ModuleList(
            nn.Sequential(Conv(x, c2, 3), Conv(c2, c2, 3), nn.Conv2d(c2, 4 * self.reg_max, 1)) for x in ch)
        self.cv3 = nn.ModuleList(nn.Sequential(Conv(x, c3, 3), Conv(c3, c3, 3), nn.Conv2d(c3, self.nc, 1)) for x in ch)
        self.dfl = DFL(self.reg_max) if self.reg_max > 1 else nn.Identity()

    def forward(self, x):
        """Concatenates and returns predicted bounding boxes and class probabilities."""
        shape = x[0].shape  # BCHW
        for i in range(self.nl):
            x[i] = torch.cat((self.cv2[i](x[i]), self.cv3[i](x[i])), 1)
        if self.training:
            return x
        elif self.dynamic or self.shape != shape:
            self.anchors, self.strides = (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5))
            self.shape = shape

        x_cat = torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2)
        if self.export and self.format in ('saved_model', 'pb', 'tflite', 'edgetpu', 'tfjs'):  # avoid TF FlexSplitV ops
            box = x_cat[:, :self.reg_max * 4]
            cls = x_cat[:, self.reg_max * 4:]
        else:
            box, cls = x_cat.split((self.reg_max * 4, self.nc), 1)
        dbox = dist2bbox(self.dfl(box), self.anchors.unsqueeze(0), xywh=True, dim=1) * self.strides

        if self.export and self.format in ('tflite', 'edgetpu'):
            # Normalize xywh with image size to mitigate quantization error of TFLite integer models as done in YOLOv5:
            # https://github.com/ultralytics/yolov5/blob/0c8de3fca4a702f8ff5c435e67f378d1fce70243/models/tf.py#L307-L309
            # See this PR for details: https://github.com/ultralytics/ultralytics/pull/1695
            img_h = shape[2] * self.stride[0]
            img_w = shape[3] * self.stride[0]
            img_size = torch.tensor([img_w, img_h, img_w, img_h], device=dbox.device).reshape(1, 4, 1)
            dbox /= img_size

        y = torch.cat((dbox, cls.sigmoid()), 1)
        return y if self.export else (y, x)

    def bias_init(self):
        """Initialize Detect() biases, WARNING: requires stride availability."""
        m = self  # self.model[-1]  # Detect() module
        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1
        # ncf = math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum())  # nominal class frequency
        for a, b, s in zip(m.cv2, m.cv3, m.stride):  # from
            a[-1].bias.data[:] = 1.0  # box
            b[-1].bias.data[:m.nc] = math.log(5 / m.nc / (640 / s) ** 2)  # cls (.01 objects, 80 classes, 640 img)




class Segment(Detect):
    """YOLOv8 Segment head for segmentation models."""

    def __init__(self, nc=80, nm=32, npr=256, ch=()):
        """Initialize the YOLO model attributes such as the number of masks, prototypes, and the convolution layers."""
        super().__init__(nc, ch)
        self.nm = nm  # number of masks
        self.npr = npr  # number of protos
        self.proto = Proto(ch[0], self.npr, self.nm)  # protos
        self.detect = Detect.forward

        c4 = max(ch[0] // 4, self.nm)
        self.cv4 = nn.ModuleList(nn.Sequential(Conv(x, c4, 3), Conv(c4, c4, 3), nn.Conv2d(c4, self.nm, 1)) for x in ch)

    def forward(self, x):
        """Return model outputs and mask coefficients if training, otherwise return outputs and mask coefficients."""
        p = self.proto(x[0])  # mask protos
        bs = p.shape[0]  # batch size

        mc = torch.cat([self.cv4[i](x[i]).view(bs, self.nm, -1) for i in range(self.nl)], 2)  # mask coefficients
        x = self.detect(self, x)
        if self.training:
            return x, mc, p
        return (torch.cat([x, mc], 1), p) if self.export else (torch.cat([x[0], mc], 1), (x[1], mc, p))


class ExtendedSegment(Segment):
    """Extends the Segment class to add a regression head predicting a 6D vector."""

    def __init__(self, nc=80, nm=32, npr=256, ch=()):
        super().__init__(nc, nm, npr, ch)
        self.regression_head = nn.ModuleList(nn.Sequential(
            Conv(x, max(x // 4, 128), 3),
            nn.Conv2d(max(x // 4, 128), 5, 1),
            nn.Sigmoid()
            ) for x in ch)  # Produces a 6D vector for each anchor and applies sigmoid activation

    def forward(self, x):
        regression_outputs = [self.regression_head[i](x[i]).view(x[i].shape[0], 5, -1) for i in range(self.nl)]
        regression_tensor = torch.cat(regression_outputs, 2)
        outputs = super().forward(x)

        # Call the parent's forward method to get original outputs and masks
        if self.training:
            x, mc, p = outputs

            return x, mc, p, regression_tensor

        else:

            if self.export:
                out_1, out_2 = outputs
                return (out_1, out_2, regression_tensor)  
            else:
                out_1, out_2 = outputs
                return ((out_1,regression_tensor), (out_2[0],out_2[1],out_2[2], regression_tensor))

# class BasicBlock(nn.Module):
#     def __init__(self, in_channels, dropout_prob=0.0):
#         super(BasicBlock, self).__init__()
#         self.conv1 = nn.Conv2d(in_channels, in_channels, kernel_size=3, padding=1)
#         self.bn1 = nn.BatchNorm2d(in_channels)
#         self.relu = nn.ReLU(inplace=True)
#         self.dropout1 = nn.Dropout2d(p=dropout_prob)  # First Dropout2D
#         self.conv2 = nn.Conv2d(in_channels, in_channels, kernel_size=3, padding=1)
#         self.bn2 = nn.BatchNorm2d(in_channels)
#         self.dropout2 = nn.Dropout2d(p= dropout_prob)  # Second Dropout2D

#     def forward(self, x):
#         identity = x
#         out = self.conv1(x)
#         out = self.bn1(out)
#         out = self.relu(out)
#         out = self.dropout1(out)  # Applying first Dropout here
#         out = self.conv2(out)
#         out = self.bn2(out)
#         out = self.dropout2(out)  # Applying second Dropout here
#         out += identity
#         out = self.relu(out)
#         return out

# class ExtendedSegment(Segment):
#     def __init__(self, nc=80, nm=32, npr=256, ch=(), dropout_prob=0.25):
#         super().__init__(nc, nm, npr, ch)
#         self.regression_head = nn.ModuleList(
#             nn.Sequential(
#                 Conv(x, max(x // 4, 128), 3),  # Assuming Conv is defined elsewhere
#                 BasicBlock(max(x // 4, 128), dropout_prob=dropout_prob),
#                 nn.Conv2d(max(x // 4, 128), 6, 1),
#                 nn.Sigmoid()
#             ) for x in ch
#         )


#     def forward(self, x):
#         regression_outputs = [self.regression_head[i](x[i]).view(x[i].shape[0], 6, -1) for i in range(self.nl)]
#         regression_tensor = torch.cat(regression_outputs, 2)
#         outputs = super().forward(x)

#         if self.training:
#             x, mc, p = outputs
#             return x, mc, p, regression_tensor
#         else:
#             if self.export:
#                 out_1, out_2 = outputs
#                 return (out_1, out_2, regression_tensor)
#             else:
#                 out_1, out_2 = outputs
#                 return ((out_1, regression_tensor), (out_2[0], out_2[1], out_2[2], regression_tensor))
    



class Pose(Detect):
    """YOLOv8 Pose head for keypoints models."""

    def __init__(self, nc=80, kpt_shape=(17, 3), ch=()):
        """Initialize YOLO network with default parameters and Convolutional Layers."""
        super().__init__(nc, ch)
        self.kpt_shape = kpt_shape  # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
        self.nk = kpt_shape[0] * kpt_shape[1]  # number of keypoints total
        self.detect = Detect.forward

        c4 = max(ch[0] // 4, self.nk)
        self.cv4 = nn.ModuleList(nn.Sequential(Conv(x, c4, 3), Conv(c4, c4, 3), nn.Conv2d(c4, self.nk, 1)) for x in ch)

    def forward(self, x):
        """Perform forward pass through YOLO model and return predictions."""
        bs = x[0].shape[0]  # batch size
        kpt = torch.cat([self.cv4[i](x[i]).view(bs, self.nk, -1) for i in range(self.nl)], -1)  # (bs, 17*3, h*w)
        x = self.detect(self, x)
        if self.training:
            return x, kpt
        pred_kpt = self.kpts_decode(bs, kpt)
        return torch.cat([x, pred_kpt], 1) if self.export else (torch.cat([x[0], pred_kpt], 1), (x[1], kpt))

    def kpts_decode(self, bs, kpts):
        """Decodes keypoints."""
        ndim = self.kpt_shape[1]
        if self.export:  # required for TFLite export to avoid 'PLACEHOLDER_FOR_GREATER_OP_CODES' bug
            y = kpts.view(bs, *self.kpt_shape, -1)
            a = (y[:, :, :2] * 2.0 + (self.anchors - 0.5)) * self.strides
            if ndim == 3:
                a = torch.cat((a, y[:, :, 2:3].sigmoid()), 2)
            return a.view(bs, self.nk, -1)
        else:
            y = kpts.clone()
            if ndim == 3:
                y[:, 2::3].sigmoid_()  # inplace sigmoid
            y[:, 0::ndim] = (y[:, 0::ndim] * 2.0 + (self.anchors[0] - 0.5)) * self.strides
            y[:, 1::ndim] = (y[:, 1::ndim] * 2.0 + (self.anchors[1] - 0.5)) * self.strides
            return y


class Classify(nn.Module):
    """YOLOv8 classification head, i.e. x(b,c1,20,20) to x(b,c2)."""

    def __init__(self, c1, c2, k=1, s=1, p=None, g=1):  # ch_in, ch_out, kernel, stride, padding, groups
        super().__init__()
        c_ = 1280  # efficientnet_b0 size
        self.conv = Conv(c1, c_, k, s, p, g)
        self.pool = nn.AdaptiveAvgPool2d(1)  # to x(b,c_,1,1)
        self.drop = nn.Dropout(p=0.0, inplace=True)
        self.linear = nn.Linear(c_, c2)  # to x(b,c2)

    def forward(self, x):
        """Performs a forward pass of the YOLO model on input image data."""
        if isinstance(x, list):
            x = torch.cat(x, 1)
        x = self.linear(self.drop(self.pool(self.conv(x)).flatten(1)))
        return x if self.training else x.softmax(1)


class RTDETRDecoder(nn.Module):
    export = False  # export mode

    def __init__(
            self,
            nc=80,
            ch=(512, 1024, 2048),
            hd=256,  # hidden dim
            nq=300,  # num queries
            ndp=4,  # num decoder points
            nh=8,  # num head
            ndl=6,  # num decoder layers
            d_ffn=1024,  # dim of feedforward
            dropout=0.,
            act=nn.ReLU(),
            eval_idx=-1,
            # training args
            nd=100,  # num denoising
            label_noise_ratio=0.5,
            box_noise_scale=1.0,
            learnt_init_query=False):
        super().__init__()
        self.hidden_dim = hd
        self.nhead = nh
        self.nl = len(ch)  # num level
        self.nc = nc
        self.num_queries = nq
        self.num_decoder_layers = ndl

        # backbone feature projection
        self.input_proj = nn.ModuleList(nn.Sequential(nn.Conv2d(x, hd, 1, bias=False), nn.BatchNorm2d(hd)) for x in ch)
        # NOTE: simplified version but it's not consistent with .pt weights.
        # self.input_proj = nn.ModuleList(Conv(x, hd, act=False) for x in ch)

        # Transformer module
        decoder_layer = DeformableTransformerDecoderLayer(hd, nh, d_ffn, dropout, act, self.nl, ndp)
        self.decoder = DeformableTransformerDecoder(hd, decoder_layer, ndl, eval_idx)

        # denoising part
        self.denoising_class_embed = nn.Embedding(nc, hd)
        self.num_denoising = nd
        self.label_noise_ratio = label_noise_ratio
        self.box_noise_scale = box_noise_scale

        # decoder embedding
        self.learnt_init_query = learnt_init_query
        if learnt_init_query:
            self.tgt_embed = nn.Embedding(nq, hd)
        self.query_pos_head = MLP(4, 2 * hd, hd, num_layers=2)

        # encoder head
        self.enc_output = nn.Sequential(nn.Linear(hd, hd), nn.LayerNorm(hd))
        self.enc_score_head = nn.Linear(hd, nc)
        self.enc_bbox_head = MLP(hd, hd, 4, num_layers=3)

        # decoder head
        self.dec_score_head = nn.ModuleList([nn.Linear(hd, nc) for _ in range(ndl)])
        self.dec_bbox_head = nn.ModuleList([MLP(hd, hd, 4, num_layers=3) for _ in range(ndl)])

        self._reset_parameters()

    def forward(self, x, batch=None):
        from ultralytics.models.utils.ops import get_cdn_group

        # input projection and embedding
        feats, shapes = self._get_encoder_input(x)

        # prepare denoising training
        dn_embed, dn_bbox, attn_mask, dn_meta = \
            get_cdn_group(batch,
                          self.nc,
                          self.num_queries,
                          self.denoising_class_embed.weight,
                          self.num_denoising,
                          self.label_noise_ratio,
                          self.box_noise_scale,
                          self.training)

        embed, refer_bbox, enc_bboxes, enc_scores = \
            self._get_decoder_input(feats, shapes, dn_embed, dn_bbox)

        # decoder
        dec_bboxes, dec_scores = self.decoder(embed,
                                              refer_bbox,
                                              feats,
                                              shapes,
                                              self.dec_bbox_head,
                                              self.dec_score_head,
                                              self.query_pos_head,
                                              attn_mask=attn_mask)
        x = dec_bboxes, dec_scores, enc_bboxes, enc_scores, dn_meta
        if self.training:
            return x
        # (bs, 300, 4+nc)
        y = torch.cat((dec_bboxes.squeeze(0), dec_scores.squeeze(0).sigmoid()), -1)
        return y if self.export else (y, x)

    def _generate_anchors(self, shapes, grid_size=0.05, dtype=torch.float32, device='cpu', eps=1e-2):
        anchors = []
        for i, (h, w) in enumerate(shapes):
            sy = torch.arange(end=h, dtype=dtype, device=device)
            sx = torch.arange(end=w, dtype=dtype, device=device)
            grid_y, grid_x = torch.meshgrid(sy, sx, indexing='ij') if TORCH_1_10 else torch.meshgrid(sy, sx)
            grid_xy = torch.stack([grid_x, grid_y], -1)  # (h, w, 2)

            valid_WH = torch.tensor([h, w], dtype=dtype, device=device)
            grid_xy = (grid_xy.unsqueeze(0) + 0.5) / valid_WH  # (1, h, w, 2)
            wh = torch.ones_like(grid_xy, dtype=dtype, device=device) * grid_size * (2.0 ** i)
            anchors.append(torch.cat([grid_xy, wh], -1).view(-1, h * w, 4))  # (1, h*w, 4)

        anchors = torch.cat(anchors, 1)  # (1, h*w*nl, 4)
        valid_mask = ((anchors > eps) * (anchors < 1 - eps)).all(-1, keepdim=True)  # 1, h*w*nl, 1
        anchors = torch.log(anchors / (1 - anchors))
        anchors = anchors.masked_fill(~valid_mask, float('inf'))
        return anchors, valid_mask

    def _get_encoder_input(self, x):
        # get projection features
        x = [self.input_proj[i](feat) for i, feat in enumerate(x)]
        # get encoder inputs
        feats = []
        shapes = []
        for feat in x:
            h, w = feat.shape[2:]
            # [b, c, h, w] -> [b, h*w, c]
            feats.append(feat.flatten(2).permute(0, 2, 1))
            # [nl, 2]
            shapes.append([h, w])

        # [b, h*w, c]
        feats = torch.cat(feats, 1)
        return feats, shapes

    def _get_decoder_input(self, feats, shapes, dn_embed=None, dn_bbox=None):
        bs = len(feats)
        # prepare input for decoder
        anchors, valid_mask = self._generate_anchors(shapes, dtype=feats.dtype, device=feats.device)
        features = self.enc_output(valid_mask * feats)  # bs, h*w, 256

        enc_outputs_scores = self.enc_score_head(features)  # (bs, h*w, nc)

        # query selection
        # (bs, num_queries)
        topk_ind = torch.topk(enc_outputs_scores.max(-1).values, self.num_queries, dim=1).indices.view(-1)
        # (bs, num_queries)
        batch_ind = torch.arange(end=bs, dtype=topk_ind.dtype).unsqueeze(-1).repeat(1, self.num_queries).view(-1)

        # (bs, num_queries, 256)
        top_k_features = features[batch_ind, topk_ind].view(bs, self.num_queries, -1)
        # (bs, num_queries, 4)
        top_k_anchors = anchors[:, topk_ind].view(bs, self.num_queries, -1)

        # dynamic anchors + static content
        refer_bbox = self.enc_bbox_head(top_k_features) + top_k_anchors

        enc_bboxes = refer_bbox.sigmoid()
        if dn_bbox is not None:
            refer_bbox = torch.cat([dn_bbox, refer_bbox], 1)
        enc_scores = enc_outputs_scores[batch_ind, topk_ind].view(bs, self.num_queries, -1)

        embeddings = self.tgt_embed.weight.unsqueeze(0).repeat(bs, 1, 1) if self.learnt_init_query else top_k_features
        if self.training:
            refer_bbox = refer_bbox.detach()
            if not self.learnt_init_query:
                embeddings = embeddings.detach()
        if dn_embed is not None:
            embeddings = torch.cat([dn_embed, embeddings], 1)

        return embeddings, refer_bbox, enc_bboxes, enc_scores

    # TODO
    def _reset_parameters(self):
        # class and bbox head init
        bias_cls = bias_init_with_prob(0.01) / 80 * self.nc
        # NOTE: the weight initialization in `linear_init_` would cause NaN when training with custom datasets.
        # linear_init_(self.enc_score_head)
        constant_(self.enc_score_head.bias, bias_cls)
        constant_(self.enc_bbox_head.layers[-1].weight, 0.)
        constant_(self.enc_bbox_head.layers[-1].bias, 0.)
        for cls_, reg_ in zip(self.dec_score_head, self.dec_bbox_head):
            # linear_init_(cls_)
            constant_(cls_.bias, bias_cls)
            constant_(reg_.layers[-1].weight, 0.)
            constant_(reg_.layers[-1].bias, 0.)

        linear_init_(self.enc_output[0])
        xavier_uniform_(self.enc_output[0].weight)
        if self.learnt_init_query:
            xavier_uniform_(self.tgt_embed.weight)
        xavier_uniform_(self.query_pos_head.layers[0].weight)
        xavier_uniform_(self.query_pos_head.layers[1].weight)
        for layer in self.input_proj:
            xavier_uniform_(layer[0].weight)