VISSL documentation¶
VISSL is a computer vision library for state-of-the-art Self-Supervised Learning research with PyTorch. VISSL aims to accelerate the research cycle in self-supervised learning: from designing a new self-supervised task to evaluating the learned representations.
- Benchmark: Linear Image Classification
- Benchmark task: Full-finetuning
- Benchmark: Low Shot Transfer
- Benchmark: Nearest Neighbor k-means
- Benchmark task: Full finetuning on Imagenet 1% , 10% subsets
- Benchmark task: Object Detection
- Benchmark: Robustness Out-Of-Distribution (OOD)
- How to Extract Features
- Summary: Feature Eval Config Settings
- How to Load Pretrained Models
- Instance Retrieval and Copy detection Benchmarks
- Activation checkpointing to reduce model memory
- LARC for Large batch size training
- Handling invalid images in dataloader
- Resume training from iteration: Stateful data sampler
- Mixed precision training (fp16)
- Train on multiple-gpus
- Train on multiple machines
- Using SLURM
- ZeRO: Optimizer state and gradient sharding