xclele/yolov10
1
0
Fork 0
mirror of https://github.com/THU-MIG/yolov10.git synced 2025-05-23 13:34:23 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add ResNet50 and ResNet101 backbone RTDETR models (#6661)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Awsome 2023-12-03 23:57:11 +08:00 committed by GitHub
parent d12411ec0d
commit 1e1247ddee
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 144 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
ultralytics/cfg/models/rt-detr/rtdetr-l.yaml
View File

@ -13,7 +13,7 @@ backbone:
- [-1, 6, HGBlock, [48, 128, 3]] # stage 1
- [-1, 1, DWConv, [128, 3, 2, 1, False]] # 2-P3/8
- [-1, 6, HGBlock, [96, 512, 3]] # stage 2
- [-1, 6, HGBlock, [96, 512, 3]] # stage 2
- [-1, 1, DWConv, [512, 3, 2, 1, False]] # 4-P3/16
- [-1, 6, HGBlock, [192, 1024, 5, True, False]] # cm, c2, k, light, shortcut
@ -26,25 +26,25 @@ backbone:
head:
- [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 10 input_proj.2
- [-1, 1, AIFI, [1024, 8]]
- [-1, 1, Conv, [256, 1, 1]] # 12, Y5, lateral_convs.0
- [-1, 1, Conv, [256, 1, 1]] # 12, Y5, lateral_convs.0
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [7, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14 input_proj.1
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [256]] # 16, fpn_blocks.0
- [-1, 1, Conv, [256, 1, 1]] # 17, Y4, lateral_convs.1
- [-1, 1, Conv, [256, 1, 1]] # 17, Y4, lateral_convs.1
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 19 input_proj.0
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [256]] # X3 (21), fpn_blocks.1
- [-1, 3, RepC3, [256]] # X3 (21), fpn_blocks.1
- [-1, 1, Conv, [256, 3, 2]] # 22, downsample_convs.0
- [-1, 1, Conv, [256, 3, 2]] # 22, downsample_convs.0
- [[-1, 17], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [256]] # F4 (24), pan_blocks.0
- [-1, 3, RepC3, [256]] # F4 (24), pan_blocks.0
- [-1, 1, Conv, [256, 3, 2]] # 25, downsample_convs.1
- [-1, 1, Conv, [256, 3, 2]] # 25, downsample_convs.1
- [[-1, 12], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [256]] # F5 (27), pan_blocks.1
- [-1, 3, RepC3, [256]] # F5 (27), pan_blocks.1
- [[21, 24, 27], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)

42
ultralytics/cfg/models/rt-detr/rtdetr-resnet101.yaml Normal file
View File

@ -0,0 +1,42 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# RT-DETR-ResNet101 object detection model with P3-P5 outputs.
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
# [depth, width, max_channels]
l: [1.00, 1.00, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0
- [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1
- [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2
- [-1, 1, ResNetLayer, [512, 256, 2, False, 23]] # 3
- [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4
head:
- [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 5
- [-1, 1, AIFI, [1024, 8]]
- [-1, 1, Conv, [256, 1, 1]] # 7
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 9
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [256]] # 11
- [-1, 1, Conv, [256, 1, 1]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [2, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [256]] # X3 (16), fpn_blocks.1
- [-1, 1, Conv, [256, 3, 2]] # 17, downsample_convs.0
- [[-1, 12], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [256]] # F4 (19), pan_blocks.0
- [-1, 1, Conv, [256, 3, 2]] # 20, downsample_convs.1
- [[-1, 7], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [256]] # F5 (22), pan_blocks.1
- [[16, 19, 22], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)

42
ultralytics/cfg/models/rt-detr/rtdetr-resnet50.yaml Normal file
View File

@ -0,0 +1,42 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# RT-DETR-ResNet50 object detection model with P3-P5 outputs.
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
# [depth, width, max_channels]
l: [1.00, 1.00, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0
- [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1
- [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2
- [-1, 1, ResNetLayer, [512, 256, 2, False, 6]] # 3
- [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4
head:
- [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 5
- [-1, 1, AIFI, [1024, 8]]
- [-1, 1, Conv, [256, 1, 1]] # 7
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 9
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [256]] # 11
- [-1, 1, Conv, [256, 1, 1]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [2, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [256]] # X3 (16), fpn_blocks.1
- [-1, 1, Conv, [256, 3, 2]] # 17, downsample_convs.0
- [[-1, 12], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [256]] # F4 (19), pan_blocks.0
- [-1, 1, Conv, [256, 3, 2]] # 20, downsample_convs.1
- [[-1, 7], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [256]] # F5 (22), pan_blocks.1
- [[16, 19, 22], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)

16
ultralytics/cfg/models/rt-detr/rtdetr-x.yaml
View File

@ -14,7 +14,7 @@ backbone:
- [-1, 1, DWConv, [128, 3, 2, 1, False]] # 2-P3/8
- [-1, 6, HGBlock, [128, 512, 3]]
- [-1, 6, HGBlock, [128, 512, 3, False, True]] # 4-stage 2
- [-1, 6, HGBlock, [128, 512, 3, False, True]] # 4-stage 2
- [-1, 1, DWConv, [512, 3, 2, 1, False]] # 5-P3/16
- [-1, 6, HGBlock, [256, 1024, 5, True, False]] # cm, c2, k, light, shortcut
@ -30,25 +30,25 @@ backbone:
head:
- [-1, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 14 input_proj.2
- [-1, 1, AIFI, [2048, 8]]
- [-1, 1, Conv, [384, 1, 1]] # 16, Y5, lateral_convs.0
- [-1, 1, Conv, [384, 1, 1]] # 16, Y5, lateral_convs.0
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [10, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 18 input_proj.1
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [384]] # 20, fpn_blocks.0
- [-1, 1, Conv, [384, 1, 1]] # 21, Y4, lateral_convs.1
- [-1, 1, Conv, [384, 1, 1]] # 21, Y4, lateral_convs.1
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [4, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 23 input_proj.0
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [384]] # X3 (25), fpn_blocks.1
- [-1, 3, RepC3, [384]] # X3 (25), fpn_blocks.1
- [-1, 1, Conv, [384, 3, 2]] # 26, downsample_convs.0
- [-1, 1, Conv, [384, 3, 2]] # 26, downsample_convs.0
- [[-1, 21], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [384]] # F4 (28), pan_blocks.0
- [-1, 3, RepC3, [384]] # F4 (28), pan_blocks.0
- [-1, 1, Conv, [384, 3, 2]] # 29, downsample_convs.1
- [-1, 1, Conv, [384, 3, 2]] # 29, downsample_convs.1
- [[-1, 16], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [384]] # F5 (31), pan_blocks.1
- [-1, 3, RepC3, [384]] # F5 (31), pan_blocks.1
- [[25, 28, 31], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)

4
ultralytics/nn/modules/__init__.py
View File

@ -18,7 +18,7 @@ Example:
"""
from .block import (C1, C2, C3, C3TR, DFL, SPP, SPPF, Bottleneck, BottleneckCSP, C2f, C3Ghost, C3x, GhostBottleneck,
HGBlock, HGStem, Proto, RepC3)
HGBlock, HGStem, Proto, RepC3, ResNetLayer)
from .conv import (CBAM, ChannelAttention, Concat, Conv, Conv2, ConvTranspose, DWConv, DWConvTranspose2d, Focus,
GhostConv, LightConv, RepConv, SpatialAttention)
from .head import Classify, Detect, Pose, RTDETRDecoder, Segment
@ -30,4 +30,4 @@ __all__ = ('Conv', 'Conv2', 'LightConv', 'RepConv', 'DWConv', 'DWConvTranspose2d
'TransformerBlock', 'MLPBlock', 'LayerNorm2d', 'DFL', 'HGBlock', 'HGStem', 'SPP', 'SPPF', 'C1', 'C2', 'C3',
'C2f', 'C3x', 'C3TR', 'C3Ghost', 'GhostBottleneck', 'Bottleneck', 'BottleneckCSP', 'Proto', 'Detect',
'Segment', 'Pose', 'Classify', 'TransformerEncoderLayer', 'RepC3', 'RTDETRDecoder', 'AIFI',
'DeformableTransformerDecoder', 'DeformableTransformerDecoderLayer', 'MSDeformAttn', 'MLP')
'DeformableTransformerDecoder', 'DeformableTransformerDecoderLayer', 'MSDeformAttn', 'MLP', 'ResNetLayer')

40
ultralytics/nn/modules/block.py
View File

@ -9,7 +9,7 @@ from .conv import Conv, DWConv, GhostConv, LightConv, RepConv
from .transformer import TransformerBlock
__all__ = ('DFL', 'HGBlock', 'HGStem', 'SPP', 'SPPF', 'C1', 'C2', 'C3', 'C2f', 'C3x', 'C3TR', 'C3Ghost',
'GhostBottleneck', 'Bottleneck', 'BottleneckCSP', 'Proto', 'RepC3')
'GhostBottleneck', 'Bottleneck', 'BottleneckCSP', 'Proto', 'RepC3', 'ResNetLayer')
class DFL(nn.Module):
@ -331,3 +331,41 @@ class BottleneckCSP(nn.Module):
y1 = self.cv3(self.m(self.cv1(x)))
y2 = self.cv2(x)
return self.cv4(self.act(self.bn(torch.cat((y1, y2), 1))))
class ResNetBlock(nn.Module):
"""ResNet block with standard convolution layers."""
def __init__(self, c1, c2, s=1, e=4):
"""Initialize convolution with given parameters."""
super().__init__()
c3 = e * c2
self.cv1 = Conv(c1, c2, k=1, s=1, act=True)
self.cv2 = Conv(c2, c2, k=3, s=s, p=1, act=True)
self.cv3 = Conv(c2, c3, k=1, act=False)
self.shortcut = nn.Sequential(Conv(c1, c3, k=1, s=s, act=False)) if s != 1 or c1 != c3 else nn.Identity()
def forward(self, x):
"""Forward pass through the ResNet block."""
return F.relu(self.cv3(self.cv2(self.cv1(x))) + self.shortcut(x))
class ResNetLayer(nn.Module):
"""ResNet layer with multiple ResNet blocks."""
def __init__(self, c1, c2, s=1, is_first=False, n=1, e=4):
"""Initializes the ResNetLayer given arguments."""
super().__init__()
self.is_first = is_first
if self.is_first:
self.layer = nn.Sequential(Conv(c1, c2, k=7, s=2, p=3, act=True),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
else:
blocks = [ResNetBlock(c1, c2, s, e=e)]
blocks.extend([ResNetBlock(e * c2, c2, 1, e=e) for _ in range(n - 1)])
self.layer = nn.Sequential(*blocks)
def forward(self, x):
"""Forward pass through the ResNet layer."""
return self.layer(x)

5
ultralytics/nn/tasks.py
View File

@ -10,7 +10,7 @@ import torch.nn as nn
from ultralytics.nn.modules import (AIFI, C1, C2, C3, C3TR, SPP, SPPF, Bottleneck, BottleneckCSP, C2f, C3Ghost, C3x,
Classify, Concat, Conv, Conv2, ConvTranspose, Detect, DWConv, DWConvTranspose2d,
Focus, GhostBottleneck, GhostConv, HGBlock, HGStem, Pose, RepC3, RepConv,
RTDETRDecoder, Segment)
ResNetLayer, RTDETRDecoder, Segment)
from ultralytics.utils import DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, colorstr, emojis, yaml_load
from ultralytics.utils.checks import check_requirements, check_suffix, check_yaml
from ultralytics.utils.loss import v8ClassificationLoss, v8DetectionLoss, v8PoseLoss, v8SegmentationLoss
@ -700,7 +700,8 @@ def parse_model(d, ch, verbose=True): # model_dict, input_channels(3)
if m is HGBlock:
args.insert(4, n) # number of repeats
n = 1
elif m is ResNetLayer:
c2 = args[1] if args[3] else args[1] * 4
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat: