Image-CaptionUsing LSTM or Transformer to solve Image Captioning in Pytorch
Stars: ✭ 36 (-49.3%)
SightseqComputer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection
Stars: ✭ 116 (+63.38%)
OmninetOfficial Pytorch implementation of "OmniNet: A unified architecture for multi-modal multi-task learning" | Authors: Subhojeet Pramanik, Priyanka Agrawal, Aman Hussain
Stars: ✭ 448 (+530.99%)
catrImage Captioning Using Transformer
Stars: ✭ 206 (+190.14%)
efficient-annotation-cookbookOfficial implementation of "Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets" (CVPR2021)
Stars: ✭ 54 (-23.94%)
AdaptivePytorch Implementation of Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning
Stars: ✭ 97 (+36.62%)
towheeTowhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
Stars: ✭ 821 (+1056.34%)
TransPosePyTorch Implementation for "TransPose: Keypoint localization via Transformer", ICCV 2021.
Stars: ✭ 250 (+252.11%)
PDNThe official PyTorch implementation of "Pathfinder Discovery Networks for Neural Message Passing" (WebConf '21)
Stars: ✭ 44 (-38.03%)
Show-Attend-and-TellA PyTorch implementation of the paper Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Stars: ✭ 58 (-18.31%)
image-classificationA collection of SOTA Image Classification Models in PyTorch
Stars: ✭ 70 (-1.41%)
AODAOfficial implementation of "Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis"(WACV 2022/CVPRW 2021)
Stars: ✭ 44 (-38.03%)
transform-graphql⚙️ Transformer function to transform GraphQL Directives. Create model CRUD directive for example
Stars: ✭ 23 (-67.61%)
MiVOS[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion. Semi-supervised VOS as well!
Stars: ✭ 302 (+325.35%)
transformerA PyTorch Implementation of "Attention Is All You Need"
Stars: ✭ 28 (-60.56%)
LaTeX-OCRpix2tex: Using a ViT to convert images of equations into LaTeX code.
Stars: ✭ 1,566 (+2105.63%)
DeepPhonemizerGrapheme to phoneme conversion with deep learning.
Stars: ✭ 152 (+114.08%)
BossNAS(ICCV 2021) BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search
Stars: ✭ 125 (+76.06%)
OpenPromptAn Open-Source Framework for Prompt-Learning.
Stars: ✭ 1,769 (+2391.55%)
FNet-pytorchUnofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms
Stars: ✭ 204 (+187.32%)
GTSRB Keras STNGerman Traffic Sign Recognition Benchmark, Keras implementation with Spatial Transformer Networks
Stars: ✭ 48 (-32.39%)
pytorch-gpt-xImplementation of autoregressive language model using improved Transformer and DeepSpeed pipeline parallelism.
Stars: ✭ 21 (-70.42%)
OverlapPredator[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.
Stars: ✭ 293 (+312.68%)
Awesome-CaptioningA curated list of Multimodal Captioning related research(including image captioning, video captioning, and text captioning)
Stars: ✭ 56 (-21.13%)
Transformer-ocrHandwritten text recognition using transformers.
Stars: ✭ 92 (+29.58%)
visualizationa collection of visualization function
Stars: ✭ 189 (+166.2%)
nemar[CVPR2020] Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation
Stars: ✭ 120 (+69.01%)
semantic-guidanceCode for our CVPR-2021 paper on Combining Semantic Guidance and Deep Reinforcement Learning For Generating Human Level Paintings.
Stars: ✭ 19 (-73.24%)
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 (+1632.39%)
Image-CaptioiningThe objective is to process by generating textual description from an image – based on the objects and actions in the image. Using generative models so that it creates novel sentences. Pipeline type models uses two separate learning process, one for language modelling and other for image recognition. It first identifies objects in image and prov…
Stars: ✭ 20 (-71.83%)
deformer[ACL 2020] DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering
Stars: ✭ 111 (+56.34%)
MIACode for "Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations" (NeurIPS 2019)
Stars: ✭ 57 (-19.72%)
graph-transformer-pytorchImplementation of Graph Transformer in Pytorch, for potential use in replicating Alphafold2
Stars: ✭ 81 (+14.08%)
cometaCorpus of Online Medical EnTities: the cometA corpus
Stars: ✭ 31 (-56.34%)
LPDC-NetCVPR2021 paper "Learning Parallel Dense Correspondence from Spatio-Temporal Descriptorsfor Efficient and Robust 4D Reconstruction"
Stars: ✭ 27 (-61.97%)
MinTLMinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
Stars: ✭ 61 (-14.08%)
CVPR2021 PLOPOfficial code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation
Stars: ✭ 102 (+43.66%)
Vision-Language-TransformerVision-Language Transformer and Query Generation for Referring Segmentation (ICCV 2021)
Stars: ✭ 127 (+78.87%)
graphtransRepresenting Long-Range Context for Graph Neural Networks with Global Attention
Stars: ✭ 45 (-36.62%)
NiuTrans.NMTA Fast Neural Machine Translation System. It is developed in C++ and resorts to NiuTensor for fast tensor APIs.
Stars: ✭ 112 (+57.75%)
gramtionTwitter bot for generating photo descriptions (alt text)
Stars: ✭ 21 (-70.42%)
YOLOSYou Only Look at One Sequence (NeurIPS 2021)
Stars: ✭ 612 (+761.97%)
InvolutionPyTorch reimplementation of the paper "Involution: Inverting the Inherence of Convolution for Visual Recognition" (2D and 3D Involution) [CVPR 2021].
Stars: ✭ 98 (+38.03%)
transformer-sltSign Language Translation with Transformers (COLING'2020, ECCV'20 SLRTP Workshop)
Stars: ✭ 92 (+29.58%)
ProtoTreeProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021
Stars: ✭ 47 (-33.8%)
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 (-67.61%)