SimCLR and simclr-pytorch
These are competing implementations of the same algorithm that serve the same purpose—choosing between them depends on whether you prioritize community adoption and simplicity (A) or multi-GPU optimization and result fidelity (B).
About SimCLR
sthalles/SimCLR
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
This project helps machine learning engineers or researchers pre-train image recognition models without needing large, labeled datasets. It takes a collection of unlabeled images and outputs a neural network that can extract meaningful features from these images. This pre-trained network can then be fine-tuned with a smaller, labeled dataset for specific image classification tasks.
About simclr-pytorch
AndrewAtanov/simclr-pytorch
PyTorch implementation of SimCLR: supports multi-GPU training and closely reproduces results
This project helps machine learning researchers and engineers efficiently train advanced image recognition models without requiring a large dataset of labeled images. By taking unlabeled image datasets, it produces powerful image encoders that can then be used to build classifiers with significantly less labeled data. It is ideal for those working on computer vision tasks who need to extract meaningful features from images.
Scores updated daily from GitHub, PyPI, and npm data. How scores work