Update YOLOv3 and YOLOv5 YAMLs (#7574)
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Glenn Jocher
GitHub
parent
596c068b18
commit
d762496989
51 changed files with 284 additions and 304 deletions
|
|
@ -9,40 +9,38 @@ width_multiple: 1.0 # layer channel multiple
|
|||
# darknet53 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, Bottleneck, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, Bottleneck, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, Bottleneck, [1024]], # 10
|
||||
]
|
||||
- [-1, 1, Conv, [32, 3, 1]] # 0
|
||||
- [-1, 1, Conv, [64, 3, 2]] # 1-P1/2
|
||||
- [-1, 1, Bottleneck, [64]]
|
||||
- [-1, 1, Conv, [128, 3, 2]] # 3-P2/4
|
||||
- [-1, 2, Bottleneck, [128]]
|
||||
- [-1, 1, Conv, [256, 3, 2]] # 5-P3/8
|
||||
- [-1, 8, Bottleneck, [256]]
|
||||
- [-1, 1, Conv, [512, 3, 2]] # 7-P4/16
|
||||
- [-1, 8, Bottleneck, [512]]
|
||||
- [-1, 1, Conv, [1024, 3, 2]] # 9-P5/32
|
||||
- [-1, 4, Bottleneck, [1024]] # 10
|
||||
|
||||
# YOLOv3-SPP head
|
||||
head:
|
||||
[[-1, 1, Bottleneck, [1024, False]],
|
||||
[-1, 1, SPP, [512, [5, 9, 13]]],
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
|
||||
- [-1, 1, Bottleneck, [1024, False]]
|
||||
- [-1, 1, SPP, [512, [5, 9, 13]]]
|
||||
- [-1, 1, Conv, [1024, 3, 1]]
|
||||
- [-1, 1, Conv, [512, 1, 1]]
|
||||
- [-1, 1, Conv, [1024, 3, 1]] # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
|
||||
- [-2, 1, Conv, [256, 1, 1]]
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 8], 1, Concat, [1]] # cat backbone P4
|
||||
- [-1, 1, Bottleneck, [512, False]]
|
||||
- [-1, 1, Bottleneck, [512, False]]
|
||||
- [-1, 1, Conv, [256, 1, 1]]
|
||||
- [-1, 1, Conv, [512, 3, 1]] # 22 (P4/16-medium)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Bottleneck, [256, False]],
|
||||
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
|
||||
- [-2, 1, Conv, [128, 1, 1]]
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 6], 1, Concat, [1]] # cat backbone P3
|
||||
- [-1, 1, Bottleneck, [256, False]]
|
||||
- [-1, 2, Bottleneck, [256, False]] # 27 (P3/8-small)
|
||||
|
||||
[[27, 22, 15], 1, Detect, [nc]], # Detect(P3, P4, P5)
|
||||
]
|
||||
- [[27, 22, 15], 1, Detect, [nc]] # Detect(P3, P4, P5)
|
||||
|
|
|
|||
|
|
@ -9,31 +9,29 @@ width_multiple: 1.0 # layer channel multiple
|
|||
# YOLOv3-tiny backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [16, 3, 1]], # 0
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 1-P1/2
|
||||
[-1, 1, Conv, [32, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 3-P2/4
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 5-P3/8
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 7-P4/16
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 9-P5/32
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]], # 11
|
||||
[-1, 1, nn.MaxPool2d, [2, 1, 0]], # 12
|
||||
]
|
||||
- [-1, 1, Conv, [16, 3, 1]] # 0
|
||||
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 1-P1/2
|
||||
- [-1, 1, Conv, [32, 3, 1]]
|
||||
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 3-P2/4
|
||||
- [-1, 1, Conv, [64, 3, 1]]
|
||||
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 5-P3/8
|
||||
- [-1, 1, Conv, [128, 3, 1]]
|
||||
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 7-P4/16
|
||||
- [-1, 1, Conv, [256, 3, 1]]
|
||||
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 9-P5/32
|
||||
- [-1, 1, Conv, [512, 3, 1]]
|
||||
- [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]] # 11
|
||||
- [-1, 1, nn.MaxPool2d, [2, 1, 0]] # 12
|
||||
|
||||
# YOLOv3-tiny head
|
||||
head:
|
||||
[[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 15 (P5/32-large)
|
||||
- [-1, 1, Conv, [1024, 3, 1]]
|
||||
- [-1, 1, Conv, [256, 1, 1]]
|
||||
- [-1, 1, Conv, [512, 3, 1]] # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Conv, [256, 3, 1]], # 19 (P4/16-medium)
|
||||
- [-2, 1, Conv, [128, 1, 1]]
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 8], 1, Concat, [1]] # cat backbone P4
|
||||
- [-1, 1, Conv, [256, 3, 1]] # 19 (P4/16-medium)
|
||||
|
||||
[[19, 15], 1, Detect, [nc]], # Detect(P4, P5)
|
||||
]
|
||||
- [[19, 15], 1, Detect, [nc]] # Detect(P4, P5)
|
||||
|
|
|
|||
|
|
@ -9,40 +9,38 @@ width_multiple: 1.0 # layer channel multiple
|
|||
# darknet53 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, Bottleneck, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, Bottleneck, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, Bottleneck, [1024]], # 10
|
||||
]
|
||||
- [-1, 1, Conv, [32, 3, 1]] # 0
|
||||
- [-1, 1, Conv, [64, 3, 2]] # 1-P1/2
|
||||
- [-1, 1, Bottleneck, [64]]
|
||||
- [-1, 1, Conv, [128, 3, 2]] # 3-P2/4
|
||||
- [-1, 2, Bottleneck, [128]]
|
||||
- [-1, 1, Conv, [256, 3, 2]] # 5-P3/8
|
||||
- [-1, 8, Bottleneck, [256]]
|
||||
- [-1, 1, Conv, [512, 3, 2]] # 7-P4/16
|
||||
- [-1, 8, Bottleneck, [512]]
|
||||
- [-1, 1, Conv, [1024, 3, 2]] # 9-P5/32
|
||||
- [-1, 4, Bottleneck, [1024]] # 10
|
||||
|
||||
# YOLOv3 head
|
||||
head:
|
||||
[[-1, 1, Bottleneck, [1024, False]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
|
||||
- [-1, 1, Bottleneck, [1024, False]]
|
||||
- [-1, 1, Conv, [512, 1, 1]]
|
||||
- [-1, 1, Conv, [1024, 3, 1]]
|
||||
- [-1, 1, Conv, [512, 1, 1]]
|
||||
- [-1, 1, Conv, [1024, 3, 1]] # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
|
||||
- [-2, 1, Conv, [256, 1, 1]]
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 8], 1, Concat, [1]] # cat backbone P4
|
||||
- [-1, 1, Bottleneck, [512, False]]
|
||||
- [-1, 1, Bottleneck, [512, False]]
|
||||
- [-1, 1, Conv, [256, 1, 1]]
|
||||
- [-1, 1, Conv, [512, 3, 1]] # 22 (P4/16-medium)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Bottleneck, [256, False]],
|
||||
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
|
||||
- [-2, 1, Conv, [128, 1, 1]]
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 6], 1, Concat, [1]] # cat backbone P3
|
||||
- [-1, 1, Bottleneck, [256, False]]
|
||||
- [-1, 2, Bottleneck, [256, False]] # 27 (P3/8-small)
|
||||
|
||||
[[27, 22, 15], 1, Detect, [nc]], # Detect(P3, P4, P5)
|
||||
]
|
||||
- [[27, 22, 15], 1, Detect, [nc]] # Detect(P3, P4, P5)
|
||||
|
|
|
|||
|
|
@ -14,48 +14,46 @@ scales: # model compound scaling constants, i.e. 'model=yolov5n-p6.yaml' will ca
|
|||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [768]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 11
|
||||
]
|
||||
- [-1, 1, Conv, [64, 6, 2, 2]] # 0-P1/2
|
||||
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
|
||||
- [-1, 3, C3, [128]]
|
||||
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
|
||||
- [-1, 6, C3, [256]]
|
||||
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
|
||||
- [-1, 9, C3, [512]]
|
||||
- [-1, 1, Conv, [768, 3, 2]] # 7-P5/32
|
||||
- [-1, 3, C3, [768]]
|
||||
- [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64
|
||||
- [-1, 3, C3, [1024]]
|
||||
- [-1, 1, SPPF, [1024, 5]] # 11
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [768, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P5
|
||||
[-1, 3, C3, [768, False]], # 15
|
||||
- [-1, 1, Conv, [768, 1, 1]]
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
|
||||
- [-1, 3, C3, [768, False]] # 15
|
||||
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 19
|
||||
- [-1, 1, Conv, [512, 1, 1]]
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
|
||||
- [-1, 3, C3, [512, False]] # 19
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 23 (P3/8-small)
|
||||
- [-1, 1, Conv, [256, 1, 1]]
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
|
||||
- [-1, 3, C3, [256, False]] # 23 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 20], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)
|
||||
- [-1, 1, Conv, [256, 3, 2]]
|
||||
- [[-1, 20], 1, Concat, [1]] # cat head P4
|
||||
- [-1, 3, C3, [512, False]] # 26 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 16], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [768, False]], # 29 (P5/32-large)
|
||||
- [-1, 1, Conv, [512, 3, 2]]
|
||||
- [[-1, 16], 1, Concat, [1]] # cat head P5
|
||||
- [-1, 3, C3, [768, False]] # 29 (P5/32-large)
|
||||
|
||||
[-1, 1, Conv, [768, 3, 2]],
|
||||
[[-1, 12], 1, Concat, [1]], # cat head P6
|
||||
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
|
||||
- [-1, 1, Conv, [768, 3, 2]]
|
||||
- [[-1, 12], 1, Concat, [1]] # cat head P6
|
||||
- [-1, 3, C3, [1024, False]] # 32 (P6/64-xlarge)
|
||||
|
||||
[[23, 26, 29, 32], 1, Detect, [nc]], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
- [[23, 26, 29, 32], 1, Detect, [nc]] # Detect(P3, P4, P5, P6)
|
||||
|
|
|
|||
|
|
@ -14,37 +14,36 @@ scales: # model compound scaling constants, i.e. 'model=yolov5n.yaml' will call
|
|||
# YOLOv5 v6.0 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 6, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 3, C3, [1024]],
|
||||
[-1, 1, SPPF, [1024, 5]], # 9
|
||||
]
|
||||
- [-1, 1, Conv, [64, 6, 2, 2]] # 0-P1/2
|
||||
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
|
||||
- [-1, 3, C3, [128]]
|
||||
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
|
||||
- [-1, 6, C3, [256]]
|
||||
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
|
||||
- [-1, 9, C3, [512]]
|
||||
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
|
||||
- [-1, 3, C3, [1024]]
|
||||
- [-1, 1, SPPF, [1024, 5]] # 9
|
||||
|
||||
|
||||
# YOLOv5 v6.0 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
- [-1, 1, Conv, [512, 1, 1]]
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
|
||||
- [-1, 3, C3, [512, False]] # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
- [-1, 1, Conv, [256, 1, 1]]
|
||||
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
|
||||
- [-1, 3, C3, [256, False]] # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
- [-1, 1, Conv, [256, 3, 2]]
|
||||
- [[-1, 14], 1, Concat, [1]] # cat head P4
|
||||
- [-1, 3, C3, [512, False]] # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
- [-1, 1, Conv, [512, 3, 2]]
|
||||
- [[-1, 10], 1, Concat, [1]] # cat head P5
|
||||
- [-1, 3, C3, [1024, False]] # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc]], # Detect(P3, P4, P5)
|
||||
]
|
||||
- [[17, 20, 23], 1, Detect, [nc]] # Detect(P3, P4, P5)
|
||||
|
|
|
|||
|
|
@ -11,7 +11,7 @@ from ultralytics.utils.tal import TORCH_1_10, dist2bbox, dist2rbox, 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_
|
||||
from .utils import bias_init_with_prob, linear_init
|
||||
|
||||
__all__ = "Detect", "Segment", "Pose", "Classify", "OBB", "RTDETRDecoder"
|
||||
|
||||
|
|
@ -417,18 +417,18 @@ class RTDETRDecoder(nn.Module):
|
|||
"""Initializes or resets the parameters of the model's various components with predefined weights and biases."""
|
||||
# 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)
|
||||
# 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, 0.0)
|
||||
constant_(self.enc_bbox_head.layers[-1].bias, 0.0)
|
||||
for cls_, reg_ in zip(self.dec_score_head, self.dec_bbox_head):
|
||||
# linear_init_(cls_)
|
||||
# linear_init(cls_)
|
||||
constant_(cls_.bias, bias_cls)
|
||||
constant_(reg_.layers[-1].weight, 0.0)
|
||||
constant_(reg_.layers[-1].bias, 0.0)
|
||||
|
||||
linear_init_(self.enc_output[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)
|
||||
|
|
|
|||
|
|
@ -23,7 +23,7 @@ def bias_init_with_prob(prior_prob=0.01):
|
|||
return float(-np.log((1 - prior_prob) / prior_prob)) # return bias_init
|
||||
|
||||
|
||||
def linear_init_(module):
|
||||
def linear_init(module):
|
||||
"""Initialize the weights and biases of a linear module."""
|
||||
bound = 1 / math.sqrt(module.weight.shape[0])
|
||||
uniform_(module.weight, -bound, bound)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue