Comments (4)
Hi folks,
Haha, not in the first run definitely, but in the end is stable :)
@AndrewAtanov correct me if I'm wrong but it seems that we used BS 1024 for both self-supervised [1] training and linear [2] eval. Because of two augmentations per image real BS for self-supervised pre-training ends up 2048 (1024 images, 2 augmentations each).
As far as I remember, LARS and worm-up of learning rate were really important. Also, it was important to exclude BN and biases from LARS (https://github.com/AndrewAtanov/simclr-pytorch/blob/master/models/ssl.py#L608).
[1] https://github.com/AndrewAtanov/simclr-pytorch/blob/master/configs/cifar_train_epochs1000_bs1024.yaml
[2] https://github.com/AndrewAtanov/simclr-pytorch/blob/master/configs/cifar_eval.yaml
from simclr-pytorch.
Hi Chen,
Thanks for your interest. In our implementation, we use simple SGD to train a linear classifier (see this line for the reference) and didn't try to use L-BFGS.
from simclr-pytorch.
Hi Andrew,
Thanks so much for your quick reply.
In my own implementation, I can only get 91.5% with 512 batch and 1000 epochs. What do think is the necessary module to reproduce the result? Or you get the 93.5% in your first try?
from simclr-pytorch.
Hi Senya,
Thanks so much for your detailed suggestions! I will try it now.
from simclr-pytorch.
Related Issues (14)
- The problem of the top 1 acc HOT 2
- Why no upscale in image augmentations?
- Use more than 4 GPU in linear evaluation HOT 5
- Reason for using LARGE_NUMBER HOT 1
- linear fc layer HOT 2
- Unable to download pre-trained weights HOT 1
- Finetuning
- Question regarding BatchNorm1dNoBias HOT 4
- whats cifar_head? HOT 1
- Checkpoints and linear evaluation HOT 1
- no image normalization HOT 2
- Training log
- Learning rate in pretraining on CIFAR10 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 simclr-pytorch.