This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.
- ade20k
- swin-transformer
- upernet
- semantic-segmentation
108,094 visible repositories in the index
433–456 of 654 · Most stars
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.
LLM KV cache compression made easy
Non-invasive decoding of typed sentences from MEG and EEG brain recordings using a convolutional encoder, transformer, and character-level language model.
Official Pytorch implementation of CutMix regularizer
A machine learning primer built from first principles. For engineers who want to reason about ML systems the way they reason about software systems.
[CVPR'25]Tora: Trajectory-oriented Diffusion Transformer for Video Generation
Python interface to PROJ (cartographic projections and coordinate transformations library)
GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
提供百度坐标系(bd-09)、火星坐标系(国测局坐标系、gcj02)、WGS84坐标系直接的坐标互转,也提供了解析高德地址的方法的python版本
Salesforce Enterprise Deep Research
Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"
🔥 Blazing fast bulk data transfers between any cloud 🔥
Neural Network Compression Framework for enhanced OpenVINO™ inference
Implementation of various self-attention mechanisms focused on computer vision. Ongoing repository.
Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch
An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"
Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]
A playground for neuro-san
视频音频生成字幕,生成srt文件。无需申请第三方API,本地实现音频转文本。基于Transformer的视频字幕生成框架。A GUI tool for generating subtitle from videos and generating srt files.
AssetFurnace: the most complete open-source image-to-3D pipeline (Oct 2026). Prompt or picture → textured, rigged, animated game character, locally on Apple Silicon or NVIDIA. Pixal3D, TRELLIS.2, Hunyuan3D, SF3D, auto-rig and 21 moves. For indie game devs and 3D artists. Free, Apache-2.0.
Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch
HaMeR: Reconstructing Hands in 3D with Transformers
明医 (MING):中文医疗问诊大模型