facebookresearch / dropoutLinks
Code release for "Dropout Reduces Underfitting"
☆317Updated 2 years ago
Alternatives and similar repositories for dropout
Users that are interested in dropout are comparing it to the libraries listed below
Sorting:
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆210Updated 2 years ago
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆219Updated 2 years ago
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆499Updated last year
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆252Updated 3 years ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆337Updated 8 months ago
- ☆190Updated 2 years ago
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆386Updated 2 years ago
- ☆209Updated 2 years ago
- Probing the representations of Vision Transformers.☆336Updated 3 years ago
- A framework for merging models solving different tasks with different initializations into one multi-task model without any additional tr…☆308Updated last year
- [NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows …☆133Updated 3 years ago
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆230Updated last year
- ☆210Updated 3 years ago
- ☆187Updated last year
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆125Updated last year
- ☆134Updated 2 years ago
- Official implementation of "Active Image Indexing"☆59Updated 2 years ago
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆384Updated last year
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆207Updated 2 years ago
- Code release for "Improved baselines for vision-language pre-training"☆61Updated last year
- Official repository for "Revisiting Weakly Supervised Pre-Training of Visual Perception Models". https://arxiv.org/abs/2201.08371.☆182Updated 3 years ago
- TF/Keras code for DiffStride, a pooling layer with learnable strides.☆124Updated 3 years ago
- Implementation of Discrete Key / Value Bottleneck, in Pytorch☆88Updated 2 years ago
- Official PyTorch implementation of the paper: "Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results" (2022)☆193Updated 2 years ago
- Official code for "TOAST: Transfer Learning via Attention Steering"☆188Updated 2 years ago
- understanding model mistakes with human annotations☆106Updated 2 years ago
- VICRegL official code base☆231Updated 2 years ago
- A library that contains a rich collection of performant PyTorch model metrics, a simple interface to create new metrics, a toolkit to fac…☆244Updated 2 months ago
- Optimized library for large-scale extraction of frames and audio from video.☆205Updated 2 years ago
- ☆293Updated 11 months ago