Comments (2)
@WarBean I also noticed this phenomenon before, but I did not test it massively to figure out why manual bp implementation is faster. Actually, we provide the bp code to ensure the backward can work correctly, due to earlier version of pytorch (<0.4) obtain a wrong result. So I cautiously thought the autograd engine may not perform perfectly, and many "extra operations" are needed to maintain better generality.
from fast-mpn-cov.
@jiangtaoxie So it is better to use manual backward implementation for now. Thanks!
from fast-mpn-cov.
Related Issues (20)
- Downloading problem? HOT 8
- CUB-200-20122数据集实验 HOT 2
- Should we use SVMs for FGVC? HOT 2
- fine tune issue HOT 4
- When will you update the Fine-grained classification results of resnet101 HOT 4
- Loss and Accuracy dont change HOT 2
- what are suggested training parameters for CUB_200_2001? HOT 4
- can't download the pretrained pth HOT 1
- The performance of released model 'mpncovresnet50-15991845.pth' HOT 4
- the result of the combination of mpncov & efficientnet did not meet expectations
- About the implementation of MPNCOV meta layer in pytorch 0.3.1
- About the post-compensation implementation using trace
- Model parameters
- 模型参数下载 HOT 3
- gradcheck for Sqrtm in MPNCOV.py
- where should I put the pre-training model? HOT 1
- RuntimeError: Error(s) in loading state_dict for DataParallel: HOT 4
- Fatal IO error: client killed HOT 5
- 1D version of Fast-MPN-Cov HOT 5
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 fast-mpn-cov.