MambaVision
NVlabs
2,256星标+224小时
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
机器学习 · GitHub
发现模型训练、评估与推理框架，比较深度学习和机器学习项目的社区关注度。
实用 GitHub 项目
4,743 个项目
SegFormer
NVlabs
3,711星标+224小时
Official PyTorch implementation of SegFormer
sionna
NVlabs
1,677星标+224小时
Sionna: An Open-Source Library for Research on Communication Systems
tirex-2
NX-AI
163星标+224小时
TiRex-2: A Zero-Shot Timeseries Forecasting Model
xlstm
NX-AI
2,218星标+224小时
Official repository of the xLSTM.
Tengine
OAID
4,535星标+224小时
Tengine 是一款面向嵌入式设备的轻量、高性能、模块化推理引擎
sahi
obss
5,602星标+224小时
与框架无关的切片/分块推理、交互式 UI 和误差分析图表
models
onnx
9,858星标+224小时
A collection of pre-trained, state-of-the-art models in the ONNX format
onnx
onnx
21,673星标+224小时
机器学习互操作性的开放标准
mmpose
open-mmlab
8,053星标+224小时
OpenMMLab 姿态估计工具箱与基准测试。
opencv_zoo
opencv
1,126星标+224小时
OpenCV DNN 模型库及基准测试。
CTranslate2
OpenNMT
4,751星标+224小时
Transformer 模型的快速推理引擎
- Fast and efficient execution on CPU and GPUThe execution is significantly faster and requires less resources than general-purpose deep learning frameworks on supported models and tasks thanks to many advanced optimizations: layer fusion, padding removal, batch reordering, in-place operations, caching mechanism, etc.
- Quantization and reduced precisionThe model serialization and computation support weights with reduced precision: 16-bit floating points (FP16), 16-bit brain floating points (BF16), 16-bit integers (INT16), 8-bit integers (INT8) and AWQ quantization (INT4).
optiland
optiland
1,066星标+224小时
Comprehensive optical design, optimization, and analysis in Python, including GPU-accelerated and differentiable ray tracing via PyTorch.
- 🛠️ Design & Modeling - Configure fields, wavelengths, apertures. Build systems using spherical, aspheric, conic, and freeform surfaces.
- 🧮 Differentiable Core - Switch between NumPy (CPU) and PyTorch (GPU/autograd) seamlessly for hybrid physics-ML workflows.
deep-learning-from-scratch
oreilly-japan
4,910星标+224小时
《从零开始的深度学习》（O'Reilly Japan，2016）
awesome-artificial-intelligence
owainlewis
16,823星标+224小时
人工智能（AI）课程、书籍、视频讲座和论文精选列表。
CUDATutorial
PaddleJitLab
1,165星标+224小时
A self-learning tutorail for CUDA High Performance Programing.
3W
petrobras
541星标+224小时
Timely detections for more proactive and effective actions in offshore oil wells!
gensim
piskvorky
16,515星标+224小时
面向人类的主题建模
- All algorithms are memory-independent w.r.t. the corpus size (can process input larger than RAM, streamed, out-of-core),
- easy to plug in your own input corpus/datastream (trivial streaming API)
omnisafe
PKU-Alignment
1,168星标+224小时
JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.
transparent-background
plemeri
1,306星标+224小时
This is a background removing tool powered by InSPyReNet (ACCV 2022)
plexe
plexe-ai
2,650星标+224小时
✨ Build a machine learning model from a prompt
PointTransformerV3
Pointcept
1,999星标+224小时
[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3). Also a pip-installable PyTorch + Triton package with pretrained Sonata, Concerto, and Utonia encoders.
- Oct 2026: PTv3 is now a pip package, point-transformer-v3, with optimizations from Pointcept2, our next codebase. It needs no spconv or FlashAttention (plain PyTorch with Triton kernels), runs 1.7-4.7x faster with 18-31% less memory on the GPU, also runs on the CPU, and loads the Sonata, Concerto and Utonia weights. See docs/acceleration.md.
- Apr 2024: PTv3 is selected as one of the 90 Oral presentations of CVPR'24.
Awesome-Prompt-Engineering
promptslab
6,446星标+224小时
This repository contains a hand-curated resources for Prompt Engineering with a focus on Generative Pre-trained Transformer (GPT), ChatGPT, PaLM etc
ao
pytorch
3,027星标+224小时
PyTorch native quantization for training and inference