qubvel / ttach
Image Test Time Augmentation with PyTorch!
☆966Updated last year
Related projects: ⓘ
- PyTorch extensions for fast R&D prototyping and Kaggle farming☆1,512Updated this week
- Official Pytorch implementation of CutMix regularizer☆1,214Updated 4 years ago
- PyTorch implementation of EfficientNetV2 family☆451Updated 2 years ago
- Gradually-Warmup Learning Rate Scheduler for PyTorch☆971Updated 3 years ago
- Augmentations usage examples for albumentations library☆421Updated last month
- The official Pytorch implementation of OCNet, OCRNet, and SegFix.☆1,187Updated last month
- label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful☆2,159Updated last year
- This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation…☆1,151Updated 2 years ago
- Copy-paste augmentation for segmentation and detection tasks☆545Updated 2 years ago
- Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method…☆1,717Updated last year
- [CVPR 2021] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers☆1,044Updated 2 weeks ago
- Semi-Supervised Learning, Object Detection, ICCV2021☆900Updated 3 months ago
- This is a PyTorch re-implementation of Axial-DeepLab (ECCV 2020 Spotlight)☆446Updated 3 years ago
- Implementation of the Swin Transformer in PyTorch.☆779Updated 3 years ago
- Implementation of various self-attention mechanisms focused on computer vision. Ongoing repository.☆1,166Updated 3 years ago
- This Repository is implementation of majority of Semantic Segmentation Loss Functions☆546Updated last year
- This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423☆1,025Updated 3 years ago
- Code for the Lovász-Softmax loss (CVPR 2018)☆1,378Updated 5 months ago
- This is an official implementation for "Self-Supervised Learning with Swin Transformers".☆618Updated 3 years ago
- Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)☆1,337Updated 2 years ago
- 🛠 Toolbox to extend PyTorch functionalities☆416Updated 4 months ago
- Unofficial PyTorch Reimplementation of RandAugment.☆627Updated last year
- PyTorch Implementation of Focal Loss and Lovasz-Softmax Loss☆332Updated 2 years ago
- A Simple pytorch implementation of GradCAM and GradCAM++☆357Updated 5 years ago
- Official implementation of PVT series☆1,708Updated last year
- PyTorch implementations of recent Computer Vision tricks (ReXNet, RepVGG, Unet3p, YOLOv4, CIoU loss, AdaBelief, PolyLoss, MobileOne). Oth…☆314Updated this week
- (ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"☆1,067Updated last year
- Compute CNN receptive field size in pytorch in one line☆348Updated 4 months ago
- This is a list of awesome methods about data augmentation.☆776Updated 3 years ago
- ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet☆1,141Updated 10 months ago