SwinIRSwinIR: Image Restoration Using Swin Transformer (official repository)
Stars: ✭ 1,260 (+115.02%)
Uformer[CVPR 2022] Official repository for the paper "Uformer: A General U-Shaped Transformer for Image Restoration".
Stars: ✭ 415 (-29.18%)
Hrnet Semantic SegmentationThe OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
Stars: ✭ 2,369 (+304.27%)
CResMD(ECCV 2020) Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration
Stars: ✭ 92 (-84.3%)
CWRCode and dataset for Single Underwater Image Restoration by Contrastive Learning, IGARSS 2021, oral.
Stars: ✭ 43 (-92.66%)
transformer-lsOfficial PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).
Stars: ✭ 201 (-65.7%)
PDNThe official PyTorch implementation of "Pathfinder Discovery Networks for Neural Message Passing" (WebConf '21)
Stars: ✭ 44 (-92.49%)
Voice2MeshCVPR 2022: Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?
Stars: ✭ 67 (-88.57%)
image-classificationA collection of SOTA Image Classification Models in PyTorch
Stars: ✭ 70 (-88.05%)
XpersonaXPersona: Evaluating Multilingual Personalized Chatbot
Stars: ✭ 54 (-90.78%)
Transformer-ocrHandwritten text recognition using transformers.
Stars: ✭ 92 (-84.3%)
deformer[ACL 2020] DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering
Stars: ✭ 111 (-81.06%)
ffhqr-datasetFFHQR -- the first large-scale retouching dataset for computer vision research.
Stars: ✭ 85 (-85.49%)
transformer-sltSign Language Translation with Transformers (COLING'2020, ECCV'20 SLRTP Workshop)
Stars: ✭ 92 (-84.3%)
ihradis-cnn-deblurImage deblurring with Convolutional Neural Networks. Scripts & Neural network models available here
Stars: ✭ 60 (-89.76%)
TransPosePyTorch Implementation for "TransPose: Keypoint localization via Transformer", ICCV 2021.
Stars: ✭ 250 (-57.34%)
enformer-pytorchImplementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch
Stars: ✭ 146 (-75.09%)
OverlapPredator[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.
Stars: ✭ 293 (-50%)
transformerA PyTorch Implementation of "Attention Is All You Need"
Stars: ✭ 28 (-95.22%)
BossNAS(ICCV 2021) BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search
Stars: ✭ 125 (-78.67%)
visualizationa collection of visualization function
Stars: ✭ 189 (-67.75%)
OpenPromptAn Open-Source Framework for Prompt-Learning.
Stars: ✭ 1,769 (+201.88%)
speech-transformerTransformer implementation speciaized in speech recognition tasks using Pytorch.
Stars: ✭ 40 (-93.17%)
LightFieldReconstructionHigh-Dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction
Stars: ✭ 50 (-91.47%)
text2keywordsTrained T5 and T5-large model for creating keywords from text
Stars: ✭ 53 (-90.96%)
LaTeX-OCRpix2tex: Using a ViT to convert images of equations into LaTeX code.
Stars: ✭ 1,566 (+167.24%)
golgothaContextualised Embeddings and Language Modelling using BERT and Friends using R
Stars: ✭ 39 (-93.34%)
towheeTowhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
Stars: ✭ 821 (+40.1%)
Vision-Language-TransformerVision-Language Transformer and Query Generation for Referring Segmentation (ICCV 2021)
Stars: ✭ 127 (-78.33%)
transform-graphql⚙️ Transformer function to transform GraphQL Directives. Create model CRUD directive for example
Stars: ✭ 23 (-96.08%)
CSV2RDFStreaming, transforming, SPARQL-based CSV to RDF converter. Apache license.
Stars: ✭ 48 (-91.81%)
YOLOv5-Lite🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 930+kb (int8) and 1.7M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~
Stars: ✭ 1,230 (+109.9%)
THREE.HighresHigh resolution and depth rendering to PNG for Three.js
Stars: ✭ 28 (-95.22%)
Walk-TransformerFrom Random Walks to Transformer for Learning Node Embeddings (ECML-PKDD 2020) (In Pytorch and Tensorflow)
Stars: ✭ 26 (-95.56%)
GTSRB Keras STNGerman Traffic Sign Recognition Benchmark, Keras implementation with Spatial Transformer Networks
Stars: ✭ 48 (-91.81%)
Super-Resolution-Meta-Attention-NetworksOpen source single image super-resolution toolbox containing various functionality for training a diverse number of state-of-the-art super-resolution models. Also acts as the companion code for the IEEE signal processing letters paper titled 'Improving Super-Resolution Performance using Meta-Attention Layers’.
Stars: ✭ 17 (-97.1%)
graph-transformer-pytorchImplementation of Graph Transformer in Pytorch, for potential use in replicating Alphafold2
Stars: ✭ 81 (-86.18%)
DMENet[CVPR 2019] Official TensorFlow Implementation for "Deep Defocus Map Estimation using Domain Adaptation"
Stars: ✭ 86 (-85.32%)
TS-CAMCodes for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization.
Stars: ✭ 96 (-83.62%)
cometaCorpus of Online Medical EnTities: the cometA corpus
Stars: ✭ 31 (-94.71%)
MinTLMinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
Stars: ✭ 61 (-89.59%)
Face-RenovationOfficial repository of the paper "HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment".
Stars: ✭ 245 (-58.19%)
pytorch-gpt-xImplementation of autoregressive language model using improved Transformer and DeepSpeed pipeline parallelism.
Stars: ✭ 21 (-96.42%)
NiuTrans.NMTA Fast Neural Machine Translation System. It is developed in C++ and resorts to NiuTensor for fast tensor APIs.
Stars: ✭ 112 (-80.89%)
YOLOSYou Only Look at One Sequence (NeurIPS 2021)
Stars: ✭ 612 (+4.44%)
Trident-Dehazing-NetworkNTIRE 2020 NonHomogeneous Dehazing Challenge (CVPR Workshop 2020) 1st Solution.
Stars: ✭ 42 (-92.83%)
DeepPhonemizerGrapheme to phoneme conversion with deep learning.
Stars: ✭ 152 (-74.06%)
verseagilityRamp up your custom natural language processing (NLP) task, allowing you to bring your own data, use your preferred frameworks and bring models into production.
Stars: ✭ 23 (-96.08%)