PyTorch SimCLR: A Simple Framework for Contrastive Learning of Visual Representations


Blog post with full documentation: Exploring SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

Image of SimCLR Arch

See also PyTorch Implementation for BYOL – Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning.


$ conda env create --name simclr --file env.yml
$ conda activate simclr
$ python

Config file

Before running SimCLR, make sure you choose the correct running configurations. You can change the running configurations by passing keyword arguments to the file.

$ python -data ./datasets --dataset-name stl10 --log-every-n-steps 100 --epochs 100 

If you want to run it on CPU (for debugging purposes) use the --disable-cuda option.

For 16-bit precision GPU training, there NO need to to install NVIDIA apex. Just use the --fp16_precision flag and this implementation will use Pytorch built in AMP training.

Feature Evaluation

Feature evaluation is done using a linear model protocol.

First, we learned features using SimCLR on the STL10 unsupervised set. Then, we train a linear classifier on top of the frozen features from SimCLR. The linear model is trained on features extracted from the STL10 train set and evaluated on the STL10 test set.

Check the Open In Colab notebook for reproducibility.

Note that SimCLR benefits from longer training.

Linear Classification Dataset Feature Extractor Architecture Feature dimensionality Projection Head dimensionality Epochs Top1 %
Logistic Regression (Adam) STL10 SimCLR ResNet-18 512 128 100 74.45
Logistic Regression (Adam) CIFAR10 SimCLR ResNet-18 512 128 100 69.82
Logistic Regression (Adam) STL10 SimCLR ResNet-50 2048 128 50 70.075