Comments (2)
At this time there can be significant overhead because the layers have not been optimized by the deep learning platforms yet. Simply calling the im2col function without doing anything can take longer than the convolution layer. We have to tolerate it before it is integrated into pytorch.
from deconvolution.
@yechengxi According to your segmentation experiments, we also find that the overall runtime of ResNet-101 FCN w/ Deconvolution is nearly 2x compared with the runtime ResNet-101 FCN w/ SyncBN.
Hoping to see the optimized version soon.
from deconvolution.
Related Issues (10)
- An exiting work!!! And there is not net_util.py. You may miss it. (: HOT 1
- Accuracy caclulation bug
- inference time HOT 1
- 1d please HOT 3
- Implementation details HOT 2
- Concerns on the segmentation performance gap based on Sync-BN HOT 13
- Depthwise convolutions HOT 1
- License? HOT 2
- FastDeconv breaks when no bias is used HOT 2
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 deconvolution.