simsiam-cifar10
simsiam-cifar10 copied to clipboard
Code to train the SimSiam model on cifar10 using PyTorch
A minimal PyTorch example of training SimSiam on CIFAR10 with a kNN predictor to report the accuracy after each epoch. The code uses lightlys version of SimSiam.
Final test set accuracy is 91% which is similar to the original paper.
Installation
pip install requirements.txt
Dependencies
This code uses SimSiam provided by lightly. We use PyTorch Lightning for the training loop. There is another example of using SimSiam with lighlty and plain PyTorch here.
Train SimSiam on CIFAR10
Training on a V100 GPU takes around 8 hours for 800 epochs and reaches around 91% accuracy on the test set.
You can run training using the following command:
python main.py
The main.py
script is kept very simple. You can modify common parameters such
as number of epochs, batch size, number of workers etc.
The default values are:
- num_workers = 8
- max_epochs = 800
- knn_k = 200
- knn_t = 0.1
- classes = 10
- batch_size = 512
- seed=1
Here are the tensorboard plots:
You can access the tensorboard logs using
tensorboard --logdir lightning_logs/