Skip to content
项目分类

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

12,808 个项目

product-nets

Atomu2014

372星标

Tensorflow implementation of Product-based Neural Networks. An extended version is at https://github.com/Atomu2014/product-nets-distributed.

OpenTranscribe

attevon-llc

114星标
OpenTranscribe preview

Self-hosted AI-powered transcription platform with speaker diarization, search, and collaboration features. Built with Svelte, FastAPI, and Docker for easy deployment.

  • Time-Stamped Comments: Add annotations at specific moments
  • User Management: Role-based access control (user / admin / super admin) with personalized settings
机器学习PythonAGPL-3.0GitHub

GsplatLoc

AtticusZeller

96星标
GsplatLoc preview

😎 GsplatLoc 🎯: Ultra-Precise Pose Optimization via 3D Gaussian Reprojection 🌟

kann

attractivechaos

764星标

A lightweight C library for artificial neural networks

  • Flexible. Model construction by building a computational graph with operators. Support RNNs, weight sharing and multiple inputs/outputs.
  • Efficient. Reasonably optimized matrix product and convolution. Support mini-batching and effective multi-threading. Sometimes faster than mainstream frameworks in their CPU-only mode.

FullSubNet

Audio-WestlakeU

617星标

PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."

NBSS

Audio-WestlakeU

383星标
NBSS preview

The official repo of NBC & SpatialNet for multichannel speech separation, denoising, and dereverberation

torch-pesq

audiolabs

231星标

PyTorch implementation of the Perceptual Evaluation of Speech Quality for wideband audio

32星标

ChemBFN: Bayesian Flow Network Framework for Chemistry Tasks. Developed in Hiroshima University.

  • SMILES or SELFIES-based de novo molecule generation
  • Protein sequence de novo generation
机器学习PythonAGPL-3.0GitHub

Keras-FCN

aurora95

649星标
Keras-FCN preview

Keras-tensorflow implementation of Fully Convolutional Networks for Semantic Segmentation(Unfinished)

Auto-DL

Auto-DL

206星标

Auto-DL helps you make Deep Learning models without writing a single line of code and giving as little input as possible.

机器学习JavaScriptGPL-3.0GitHub

UV-Net

AutodeskAILab

213星标

Code for UV-Net: Learning from Boundary Representations, CVPR 2021.

autodistill

autodistill

2,800星标
autodistill preview

Images to inference with no labeling (use foundation models to train supervised models).

  • 🔌 Pluggable interface to connect models together
  • 🤖 Automatically label datasets
机器学习PythonApache-2.0GitHub