google-deepmind / compressed_vision
☆131Updated last year
Related projects ⓘ
Alternatives and complementary repositories for compressed_vision
- ☆292Updated 4 months ago
- Named tensors with first-class dimensions for PyTorch☆322Updated last year
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆203Updated last year
- Train vision models using JAX and 🤗 transformers☆95Updated 3 weeks ago
- Optimized library for large-scale extraction of frames and audio from video.☆203Updated last year
- A light-weight implementation of ICCV2023 paper "Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Rei…☆77Updated last year
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆119Updated 3 months ago
- Internet Explorer explores the web in a self-supervised manner to progressively find relevant examples that improve performance on a desi…☆163Updated last year
- Automatically take good care of your preemptible TPUs☆32Updated last year
- Simple and efficient RevNet-Library for PyTorch with XLA and DeepSpeed support and parameter offload☆124Updated 2 years ago
- Automatic gradient descent☆206Updated last year
- ☆178Updated last year
- Implementation of Hourglass Transformer, in Pytorch, from Google and OpenAI☆84Updated 2 years ago
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆207Updated last year
- Scalable and Performant Data Loading☆66Updated this week
- Code release for "Dropout Reduces Underfitting"☆312Updated last year
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆247Updated 2 years ago
- JAX implementation ViT-VQGAN☆55Updated 2 years ago
- Contrastive Language-Image Pretraining☆143Updated 2 years ago
- Unofficial JAX implementations of deep learning research papers☆151Updated 2 years ago
- ☆53Updated 10 months ago
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)☆185Updated 2 years ago
- Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper☆79Updated 3 years ago
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆203Updated last year
- Implementation of Discrete Key / Value Bottleneck, in Pytorch☆87Updated last year
- Easy Hypernetworks in Pytorch and Jax☆96Updated last year
- Multidimensional indexing for tensors☆113Updated last year