Comments (4)
Hi @MangekyoSasuke
Description of eASSP in paper is not specific enough, but i have implemented it as far as i understood it form paper.
I will call it LightEfficientASPP, Author of the Modnet(@ZHKKKe ) claim eASSP has 1% of the ASSP parameters and 1% computational cost. but LightEfficientASPP has 1.8 % parameters and computational cost.
it will be so kind of @ZHKKKe if he comments on LightEfficientASPP
class LightEfficientASPP(nn.Module):
def __init__(self, in_channels, dilation_rates=[6, 12, 18], channel_reduction=4):
super(LightEfficientASPP, self).__init__()
out_channels=in_channels // channel_reduction
# Channel reduction
self.channel_reduction_conv = Conv2dIBNormRelu(in_channels, in_channels // channel_reduction, kernel_size=1)
c1_out=out_channels
c2_out=c1_out//channel_reduction
c2_out=c2_out//channel_reduction
# Depth-wise atrous convolutions with point-wise convolutions
self.conv3x3_1 = nn.Sequential(
Conv2dIBNormRelu(c1_out, c1_out, kernel_size=3, padding=dilation_rates[0], dilation=dilation_rates[0], groups=c1_out),
Conv2dIBNormRelu(c1_out, c1_out, kernel_size=1)
)
self.conv3x3_2 = nn.Sequential(
Conv2dIBNormRelu(out_channels, c2_out, kernel_size=3, padding=dilation_rates[1], dilation=dilation_rates[1], groups=c2_out),
Conv2dIBNormRelu(c2_out, c2_out, kernel_size=1)
)
self.conv3x3_3 = nn.Sequential(
Conv2dIBNormRelu(out_channels, c2_out, kernel_size=3, padding=dilation_rates[2], dilation=dilation_rates[2], groups=c2_out),
Conv2dIBNormRelu(c2_out, c2_out, kernel_size=1)
)
# Recover the number of channels
self.recover_channels = Conv2dIBNormRelu(c1_out+c2_out+c2_out, in_channels, kernel_size=1)
def forward(self, x):
reduced_features = self.channel_reduction_conv(x)
conv3x3_1 = self.conv3x3_1(reduced_features)
conv3x3_2 = self.conv3x3_2(reduced_features)
conv3x3_3 = self.conv3x3_3(reduced_features)
combined_features = torch.cat([conv3x3_1, conv3x3_2,conv3x3_3], dim=1)
output = self.recover_channels(combined_features)
return output
Thank you
from modnet.
from modnet.
How is the performance?
from modnet.
Hi @vodatvan01 ,
The Performance is pretty comparable.
from modnet.
Related Issues (20)
- Will you please release the DEMO trained model? HOT 1
- Anyone who would kindly share their training code? HOT 5
- Training Code HOT 9
- 如何设置只对人像进行识别抠图 HOT 2
- Initial performance very poor after training on P3M dataset.
- 你好,我是清华的一名学生,论文提到分割部分的backbone是mobileV2吗,这部分是否可以换成其他网络,有一些细节比较困惑,真心请教,感激不尽 HOT 1
- Whether it is possible to replace the backbone of the semantic segmentation part and change it to swintrainsformer
- inaccurate
- Fine-tuning MODNet on a custom dataset using SOC HOT 1
- How to get the label(groundtruth) of other image?
- 请问mobilenetv2_human_seg.ckpt和其他几个模型的区别在哪儿?
- I think the boundary mask is calculated wrong HOT 1
- modnet 下面模型怎么安装使用? HOT 1
- Performance different on colab demo and website demo
- edit the LRBranch and HRBranch after changed backbone HOT 3
- Single image portrait cutout. Running on GPU is not as fast as CPU
- 7M的模型在哪里? HOT 1
- 求教
- 测试的两个结果不一样。
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 modnet.