Comments (1)
endernewton
commented on August 28, 2024
The paper described the setting we used on the TPU side with TF. The code base is implemented in GPU w/ PyTorch which I find 0.1 works quite well and always stick to it (we have not tried 0.02 with this code but I believe it should also achieve reasonable results). The cause is unknown, maybe some subtle difference between GPU/TPU/TF/PT.
from simsiam.
Related Issues (20)
- loss question HOT 4
- Single GPU Training HOT 3
- Loss descent slowly HOT 1
- Checkpoints with 50 epochs HOT 1
- [Problem] problem occured when trained on custom dataset HOT 4
- difference between byol in table19 and simsiam? HOT 1
- larger batch size with linear scale does not work
- checkpoint for epoch 800
- Slow convergence with SGD linear evaluation HOT 1
- SyncBatchnorm usage in main_lincls.py HOT 2
- About the projection and prediction head dimension configs
- Loss collapse during training HOT 1
- About the shape of image[0] and image[1] HOT 1
- Pre-trained weights for SimCLR, MoCov2, BYOL, SwaV HOT 1
- The value of loss function nn.CosineSimilarity is negative HOT 1
- self.encoder.fc in builder.py
- which vector is used in experiment (the vector atfer predictor or after projection)?
- Why are training and testing so slow HOT 2
- Could not find any class folder
- Loss increasing
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 simsiam.