ResNeSt——ResNet最强改进版
论文地址:https://hangzhang.org/files/resnest.pdf
github：https://github.com/zhanghang1989/ResNeSt
1. 先来看看作者，都是大牛，感谢给我们提供优越的网络，并且开源
Caption
2. 再来看看网络的性能
在图像识别，目标检测和图像分割都有长点，说明网络的泛化能力极强。
Caption
ResNeSt在图像分类上中ImageNet数据集上超越了其前辈ResNet、ResNeXt、SENet以及EfficientNet。使用ResNeSt-50为基本骨架的Faster-RCNN比使用ResNet-50的mAP要高出3.08%。使用ResNeSt-50为基本骨架的DeeplabV3比使用ResNet-50的mIOU要高出3.02%。涨点效果非常明显。
3. 直接看重点，Split-Attention模块
Caption
从左到右分别是SENet, SKNet, ResNeSt的网络结构，Split-Attention其本质可理解为切片的注意力监督机制。
Caption
每个Cardinal的实现细节，悄悄告诉你，看代码会更加清楚哦!像不像多个SENet的组合?哈哈哈。。。
4. 开源的模型是从ResNeSt50开始的，怎么用ResNeSt18呢? 博主给你答案
在官方代码中添加下面的一段代码，就可以调用ResNeSt18了，是不是很简单。
def resnest18(pretrained=False, root='~/.encoding/models', **kwargs):
model = ResNet(Bottleneck, [2, 2, 2, 2],
radix=2, groups=1, bottleneck_width=64,
deep_stem=True, stem_width=32, avg_down=True,
avd=True, avd_first=False, **kwargs)
if pretrained:
# 官方没有提供resnest18的预训练模型，我这里用resnest50的预训练模型加载
weight = torch.hub.load_state_dict_from_url(
resnest_model_urls['resnest50'], progress=True, check_hash=True)
model_dict = model.state_dict()
for k,v in weight.items():
if k in model_dict.keys():
model_dict[k] = v
model.load_state_dict(model_dict)
return model5. 测试一下
整体代码是这样的
##+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
## Created by: Hang Zhang
## Email: [email protected]
## Copyright (c) 2020
##
## LICENSE file in the root directory of this source tree
##+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
"""ResNeSt models"""
import torch
from resnet import ResNet, Bottleneck
__all__ = ['resnest50', 'resnest101', 'resnest200', 'resnest269']
_url_format = 'https://hangzh.s3.amazonaws.com/encoding/models/{}-{}.pth'
_model_sha256 = {name: checksum for checksum, name in [
('528c19ca', 'resnest50'),
('22405ba7', 'resnest101'),
('75117900', 'resnest200'),
('0cc87c48', 'resnest269'),
]}
def short_hash(name):
if name not in _model_sha256:
raise ValueError('Pretrained model for {name} is not available.'.format(name=name))
return _model_sha256[name][:8]
resnest_model_urls = {name: _url_format.format(name, short_hash(name)) for
name in _model_sha256.keys()
}
# 博主添加的
def resnest18(pretrained=False, root='~/.encoding/models', **kwargs):
model = ResNet(Bottleneck, [2, 2, 2, 2],
radix=2, groups=1, bottleneck_width=64,
deep_stem=True, stem_width=32, avg_down=True,
avd=True, avd_first=False, **kwargs)
if pretrained:
# 官方没有提供resnest18的预训练模型，我这里用resnest50的预训练模型加载
weight = torch.hub.load_state_dict_from_url(
resnest_model_urls['resnest50'], progress=True, check_hash=True)
model_dict = model.state_dict()
for k,v in weight.items():
if k in model_dict.keys():
model_dict[k] = v
model.load_state_dict(model_dict)
return model
def resnest50(pretrained=False, root='~/.encoding/models', **kwargs):
model = ResNet(Bottleneck, [3, 4, 6, 3],
radix=2, groups=1, bottleneck_width=64,
deep_stem=True, stem_width=32, avg_down=True,
avd=True, avd_first=False, **kwargs)
if pretrained:
model.load_state_dict(torch.hub.load_state_dict_from_url(
resnest_model_urls['resnest50'], progress=True, check_hash=True))
return model
def resnest101(pretrained=False, root='~/.encoding/models', **kwargs):
model = ResNet(Bottleneck, [3, 4, 23, 3],
radix=2, groups=1, bottleneck_width=64,
deep_stem=True, stem_width=64, avg_down=True,
avd=True, avd_first=False, **kwargs)
if pretrained:
model.load_state_dict(torch.hub.load_state_dict_from_url(
resnest_model_urls['resnest101'], progress=True, check_hash=True))
return model
def resnest200(pretrained=False, root='~/.encoding/models', **kwargs):
model = ResNet(Bottleneck, [3, 24, 36, 3],
radix=2, groups=1, bottleneck_width=64,
deep_stem=True, stem_width=64, avg_down=True,
avd=True, avd_first=False, **kwargs)
if pretrained:
model.load_state_dict(torch.hub.load_state_dict_from_url(
resnest_model_urls['resnest200'], progress=True, check_hash=True))
return model
def resnest269(pretrained=False, root='~/.encoding/models', **kwargs):
model = ResNet(Bottleneck, [3, 30, 48, 8],
radix=2, groups=1, bottleneck_width=64,
deep_stem=True, stem_width=64, avg_down=True,
avd=True, avd_first=False, **kwargs)
if pretrained:
model.load_state_dict(torch.hub.load_state_dict_from_url(
resnest_model_urls['resnest269'], progress=True, check_hash=True))
return model
if __name__ == "__main__":
net = resnest18(pretrained=True)
print(net)运行一下，加载了预训练模型，ResNeSt18的网络结构如下:
ResNet(
(conv1): Sequential(
(0): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
(6): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(layer1): Sequential(
(0): Bottleneck(
(conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): SplAtConv2d(
(conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=2, bias=False)
(bn0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(fc1): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1))
(bn1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(fc2): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))
)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): AvgPool2d(kernel_size=1, stride=1, padding=0)
(1): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): SplAtConv2d(
(conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=2, bias=False)
(bn0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(fc1): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1))
(bn1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(fc2): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))
)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(layer2): Sequential(
(0): Bottleneck(
(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(avd_layer): AvgPool2d(kernel_size=3, stride=2, padding=1)
(conv2): SplAtConv2d(
(conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=2, bias=False)
(bn0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(fc1): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1))
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(fc2): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))
)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): AvgPool2d(kernel_size=2, stride=2, padding=0)
(1): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): SplAtConv2d(
(conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=2, bias=False)
(bn0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(fc1): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1))
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(fc2): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))
)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(layer3): Sequential(
(0): Bottleneck(
(conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(avd_layer): AvgPool2d(kernel_size=3, stride=2, padding=1)
(conv2): SplAtConv2d(
(conv): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=2, bias=False)
(bn0): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(fc1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(fc2): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1))
)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): AvgPool2d(kernel_size=2, stride=2, padding=0)
(1): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): SplAtConv2d(
(conv): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=2, bias=False)
(bn0): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(fc1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(fc2): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1))
)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(layer4): Sequential(
(0): Bottleneck(
(conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(avd_layer): AvgPool2d(kernel_size=3, stride=2, padding=1)
(conv2): SplAtConv2d(
(conv): Conv2d(512, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=2, bias=False)
(bn0): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(fc1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(fc2): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1))
)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): AvgPool2d(kernel_size=2, stride=2, padding=0)
(1): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(2): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): SplAtConv2d(
(conv): Conv2d(512, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=2, bias=False)
(bn0): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(fc1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(fc2): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1))
)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(avgpool): GlobalAvgPool2d()
(fc): Linear(in_features=2048, out_features=1000, bias=True)
)
就是这么简单，替换掉你的ResNet吧! 如果喜欢就给博主点个赞吧。。。
相关: https://www.cnblogs.com/xiximayou/p/12728644.html
机器之心