omihub777 / ViT-CIFAR
PyTorch implementation for Vision Transformer[Dosovitskiy, A.(ICLR'21)] modified to obtain over 90% accuracy FROM SCRATCH on CIFAR-10 with small number of parameters (= 6.3M, originally ViT-B has 86M).
☆177Updated 11 months ago
Alternatives and similar repositories for ViT-CIFAR:
Users that are interested in ViT-CIFAR are comparing it to the libraries listed below
- Compare neural networks by their feature similarity☆349Updated last year
- Let's train vision transformers (ViT) for cifar 10!☆576Updated this week
- ☆16Updated 2 years ago
- Train ImageNet *fast* in 500 lines of code with FFCV☆136Updated 8 months ago
- Implementation of ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks, ICML 2021.☆140Updated 3 years ago
- Reproduce CKA: Similarity of Neural Network Representations Revisited☆297Updated 4 years ago
- Transformers trained on Tiny ImageNet☆50Updated 2 years ago
- Implementation of Vision Transformer from scratch and performance compared to standard CNNs (ResNets) and pre-trained ViT on CIFAR10 and …☆106Updated 9 months ago
- (Pytorch) Training ResNets on ImageNet-100 data☆54Updated 2 years ago
- An Numpy and PyTorch Implementation of CKA-similarity with CUDA support☆88Updated 3 years ago
- pytorch-tiny-imagenet☆170Updated last year
- PyTorch implementation of Mixer-nano (#parameters is 0.67M, originally Mixer-S/16 has 18M) with 90.83 % acc. on CIFAR-10. Training from s…☆30Updated 3 years ago
- Unofficial implementation of MLP-Mixer: An all-MLP Architecture for Vision☆216Updated 3 years ago
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆73Updated last year
- Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch☆316Updated last year
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆339Updated 5 months ago
- Mode Connectivity and Fast Geometric Ensembles in PyTorch☆267Updated 2 years ago
- Pytorch implementation of the paper Exploring Simple Siamese Representation Learning.☆72Updated 4 years ago
- Code for the paper "On the Adversarial Robustness of Visual Transformers"☆55Updated 3 years ago
- PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)☆139Updated 2 years ago
- Pretrained models on CIFAR10/100 in PyTorch☆330Updated last year
- ☆34Updated 2 years ago
- ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."☆117Updated last year
- ImageNet-R(endition) and DeepAugment (ICCV 2021)☆259Updated 3 years ago
- Official PyTorch implementation of "Dataset Condensation via Efficient Synthetic-Data Parameterization" (ICML'22)☆108Updated last year
- This repo shows an easy way to download imagenet on a remote server☆45Updated 2 years ago
- [BMVC 2022] Official repository for "How to Train Vision Transformer on Small-scale Datasets?"☆145Updated last year
- [NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)☆176Updated 3 years ago
- The implementation of our paper: Towards Robust Vision Transformer (CVPR2022)☆140Updated 2 years ago
- ☆109Updated last year