Comments (4)
Sanster
commented on June 2, 2024
- 生成 schema 不需要训练好的权重，build 好网络结构即可
- 报错的问题最好能贴下网络结构，以及用到什么 nn.Module
from pytorch-network-slimming.
GeneralJing
commented on June 2, 2024
Net(
(detail): DetailBranch(
(S1): Sequential(
(0): ConvBNReLU(
(conv): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(1): ConvBNReLU(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(S2): Sequential(
(0): ConvBNReLU(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(1): ConvBNReLU(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): ConvBNReLU(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(S3): Sequential(
(0): ConvBNReLU(
(conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(1): ConvBNReLU(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): ConvBNReLU(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
)
(segment): SegmentBranch(
(S1S2): StemBlock(
(conv): ConvBNReLU(
(conv): Conv2d(3, 16, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(left): Sequential(
(0): ConvBNReLU(
(conv): Conv2d(16, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(1): ConvBNReLU(
(conv): Conv2d(8, 16, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(right): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(fuse): ConvBNReLU(
(conv): Conv2d(32, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(S3): Sequential(
(0): GELayerS2(
(conv1): ConvBNReLU(
(conv): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(dwconv1): Sequential(
(0): Conv2d(16, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=16, bias=False)
(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(dwconv2): Sequential(
(0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=96, bias=False)
(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(96, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(shortcut): Sequential(
(0): Conv2d(16, 16, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=16, bias=False)
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): Conv2d(16, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(1): GELayerS1(
(conv1): ConvBNReLU(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(dwconv): Sequential(
(0): Conv2d(32, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
)
(S4): Sequential(
(0): GELayerS2(
(conv1): ConvBNReLU(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(dwconv1): Sequential(
(0): Conv2d(32, 192, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(dwconv2): Sequential(
(0): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(shortcut): Sequential(
(0): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): Conv2d(32, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(1): GELayerS1(
(conv1): ConvBNReLU(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(dwconv): Sequential(
(0): Conv2d(64, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=64, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
)
(S5_4): Sequential(
(0): GELayerS2(
(conv1): ConvBNReLU(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(dwconv1): Sequential(
(0): Conv2d(64, 384, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=64, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(dwconv2): Sequential(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(shortcut): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=64, bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(1): GELayerS1(
(conv1): ConvBNReLU(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(dwconv): Sequential(
(0): Conv2d(128, 768, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=128, bias=False)
(1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(2): GELayerS1(
(conv1): ConvBNReLU(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(dwconv): Sequential(
(0): Conv2d(128, 768, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=128, bias=False)
(1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(3): GELayerS1(
(conv1): ConvBNReLU(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(dwconv): Sequential(
(0): Conv2d(128, 768, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=128, bias=False)
(1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
)
(S5_5): CEBlock(
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv_gap): ConvBNReLU(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(conv_last): ConvBNReLU(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
)
(bga): BGALayer(
(left1): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=128, bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
)
(left2): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): AvgPool2d(kernel_size=3, stride=2, padding=1)
)
(right1): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(right2): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=128, bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
)
(up1): Upsample(scale_factor=4.0, mode=nearest)
(up2): Upsample(scale_factor=4.0, mode=nearest)
(conv): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
)
(head): SegmentHead(
(conv): ConvBNReLU(
(conv): Conv2d(128, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(drop): Dropout(p=0.1, inplace=False)
(conv_out): Sequential(
(0): Identity()
(1): Conv2d(1024, 19, kernel_size=(1, 1), stride=(1, 1))
(2): Upsample(scale_factor=8.0, mode=bilinear)
)
)
)
大佬，网络的结构贴上来了，辛苦看下
from pytorch-network-slimming.
Sanster
commented on June 2, 2024
有分组卷积，分组卷积不支持🥲
from pytorch-network-slimming.
GeneralJing
commented on June 2, 2024
好的 还是自己写代码剪把
from pytorch-network-slimming.
Related Issues (12)
- 可以支持自定义网络结构剪枝吗？比如不是典型的网络结构 HOT 2
- AssertionError: len(in_keep_idxes): 2048, module.weight.shape[1]: 128
- shufflenet pruning
- Question about tracker
- 示例代码，保存的模型大小有点疑问 HOT 4
- SlimPruner使用 HOT 2
- KeyError: 'encoder.level1.conv' HOT 6
- can not pruning following network with two continuous convolution block HOT 1
- 参考 HOT 1
- conv pruning issue HOT 31
- python3 gen_schema.py --net resnet18 --save_path ./schema/resnet18.json 报错 HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pytorch-network-slimming.