Comments (5)
soumith
commented on August 11, 2024
Don't use fbcunn, it's obsolete now, i removed the fbcunn parts
from imagenet-multigpu.torch.
antoajayraj
commented on August 11, 2024
Thanks for your quick response @soumith
Would there any performance benefit that one could get by using fblualib/fbcunn with Alexnet ? I believe I should do some code changes in the Alexnet to get the fbclualib/fbcunn benefits ?? Right ?
from imagenet-multigpu.torch.
soumith
commented on August 11, 2024
No
from imagenet-multigpu.torch.
antoajayraj
commented on August 11, 2024
Is the 'No' for performance benefits or for code changes ??
from imagenet-multigpu.torch.
soumith
commented on August 11, 2024
no for perfomance benefits. i think fbcunn Convolution code is no longer perf-relevant as it has been integrated into cudnn.
from imagenet-multigpu.torch.
Related Issues (20)
- "nn/Linear.lua:69: input must be vector or matrix"
- Data loading time is different across threads
- Problem with Thread ???
- Retraining an existing model(No details) HOT 1
- How can I retrain this googlenet network? HOT 2
- I used just 2 class training. But test outputs are 4 values. Why?
- Trained googlenet's outputs are negative value. Why negative? HOT 1
- Why not call cutorch.synchronizeAll()
- just want to say "Thanks to Soumith" for this useful toolbox
- how to save my image data into torch format (.t7) HOT 3
- Can not continue training
- Training stops while running main.lua , "nClasses is reported different in the data loader, and in the commandline options" HOT 1
- AlexNet Top-1 accuracy on test dataset only reach 45% when train with multiple GPUs HOT 3
- Dropout in AlexNet
- Resume training fails - weights/gradients/input tensors on different GPUs
- SqueezeNet issue HOT 2
- Could not find any image file in the given input paths
- Training time about Multi GPUs and Single GPU HOT 1
- Data loading
- testing extremely slow
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 imagenet-multigpu.torch.