sayakpaul / FunMatch-Distillation
TF2 implementation of knowledge distillation using the "function matching" hypothesis from https://arxiv.org/abs/2106.05237.
☆87Updated 2 years ago
Related projects: ⓘ
- Implementation of Online Label Smoothing in PyTorch☆94Updated last year
- Contains code for the paper "Vision Transformers are Robust Learners" (AAAI 2022).☆121Updated last year
- Examples of using PyTorch hooks, as covered in my YouTube tutorial video.☆32Updated 10 months ago
- understanding model mistakes with human annotations☆104Updated last year
- State-of-the-art data augmentation search algorithms in PyTorch☆47Updated last year
- Minimal implementation of adaptive gradient clipping (https://arxiv.org/abs/2102.06171) in TensorFlow 2.☆79Updated 3 years ago
- [NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows …☆124Updated last year
- Visualizer for PyTorch image models☆40Updated 3 years ago
- 1st Place Solution in Google Universal Image Embedding☆57Updated last year
- AutoML for image augmentation. AutoAlbument uses the Faster AutoAugment algorithm to find optimal augmentation policies. Documentation - …☆199Updated 3 years ago
- An open source implementation of CLIP.☆32Updated last year
- ☆24Updated 2 years ago
- Simplify Your Visual Data Ops. Find and visualize issues with your computer vision datasets such as duplicates, anomalies, data leakage, …☆65Updated 11 months ago
- Official implementation of "Active Image Indexing"☆58Updated last year
- Implements MLP-Mixer (https://arxiv.org/abs/2105.01601) with the CIFAR-10 dataset.☆54Updated 2 years ago
- Pytorch augmentation☆118Updated 9 months ago
- Official PyTorch implementation of RIO☆18Updated 3 years ago
- A crash course on PyTorch hooks☆40Updated 4 years ago
- Implementation of self-supervised image-level contrastive pretraining methods using Keras.☆68Updated 2 years ago
- EfficientNet, MobileNetV3, MobileNetV2, MixNet, etc in JAX w/ Flax Linen and Objax☆126Updated 8 months ago
- Aloception is a set of package for computer vision: aloscene, alodataset, alonet.☆93Updated 9 months ago
- Contains my experiments with the `big_vision` repo to train ViTs on ImageNet-1k.☆22Updated last year
- This repository contains an overview of important follow-up works based on the original Vision Transformer (ViT) by Google.☆136Updated 2 years ago
- DETR - Faster RCNN implementation in tensorflow 2☆54Updated last year
- Implementing DropPath/StochasticDepth in PyTorch☆16Updated 2 years ago
- Finetune Google's pre-trained ViT models from HuggingFace's model hub.☆18Updated 3 years ago
- ☆47Updated 5 months ago
- Cyclemoid implementation for PyTorch☆87Updated 2 years ago
- Timm model explorer☆36Updated 5 months ago
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities☆78Updated 2 years ago