Skip to content
Project categories

Machine Learning · GitHub

Train, evaluate, and run machine learning models.

Useful GitHub projects

12,806 projects
386stars
neural-symbolic-machines preview

Neural Symbolic Machines is a framework to integrate neural networks and symbolic representations using reinforcement learning, with applications in program synthesis and semantic parsing.

Machine LearningPythonApache-2.0GitHub
724stars
pytorch-cnn-finetune preview

Fine-tune pretrained Convolutional Neural Networks with PyTorch

  • Gives access to the most popular CNN architectures pretrained on ImageNet.
  • Automatically replaces classifier on top of the network, which allows you to train a network with a dataset that has a different number of classes.

BlazePoseBarracuda

creativeIKEP

211stars

BlazePoseBarracuda is a human 2D/3D pose estimation neural network that runs the Mediapipe Pose (BlazePose) pipeline on the Unity Barracuda with GPU.

251stars

Unofficial PyTorch implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement', SIGGRAPH 2017 https://groups.csail.mit.edu/graphics/hdrnet/

GRACE

CRIPAC-DIG

358stars

[GRL+ @ ICML 2020] PyTorch implementation for "Deep Graph Contrastive Representation Learning" (https://arxiv.org/abs/2006.04131v2)

Machine LearningPythonApache-2.0GitHub

headnerf

CrisHY1995

447stars

This repository contains a pytorch implementation of "HeadNeRF: A Real-time NeRF-based Parametric Head Model (CVPR 2022)".

CausE

criteo-research

249stars

Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.

Machine LearningPythonApache-2.0GitHub

reco-gym

criteo-research

484stars

Code for reco-gym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising

Machine LearningJupyter NotebookApache-2.0GitHub

torch-l1-snr

crlandsc

45stars

Variations of L1 SNR Loss function for training audio source separation machine learning models

  • L1 Loss Blending: The l1_weight parameter allows mixing between L1SNR and standard L1 loss, softening the "all-or-nothing" behavior of pure SNR losses for more nuanced separation.
  • Multi-Resolution STFT Averaging - Extending an STFT-based loss to multiple resolutions is common in recent literature.
50stars
torch-log-wmse preview

logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.

Machine LearningPythonApache-2.0GitHub

k-diffusion

crowsonkb

2,603stars

Karras et al. (2022) diffusion models for PyTorch

  • k-diffusion supports a highly efficient hierarchical transformer model type.
  • k-diffusion supports a soft version of Min-SNR loss weighting for improved training at high resolutions with less hyperparameters than the loss weighting used in Karras et al. (2022).
657stars
Exclusively-Dark-Image-Dataset preview

Exclusively Dark (ExDARK) dataset which to the best of our knowledge, is the largest collection of low-light images taken in very low-light environments to twilight (i.e 10 different conditions) to-date with image class and object level annotations.

Machine LearningMATLABBSD-3-ClauseGitHub

gandissect

CSAILVision

1,765stars
gandissect preview

Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/