Stars
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
PyTorch extensions for fast R&D prototyping and Kaggle farming
Machine/deep learning papers that address the topic of privacy in visual data.
Programmatically generate SVG (vector) images, animations, and interactive Jupyter widgets
Rich is a Python library for rich text and beautiful formatting in the terminal.
Python module for data scientists for quick creating annotation projects.
Visualizer for neural network, deep learning and machine learning models
Batch normalization fusion for PyTorch. This is an archived repository, which is not maintained.
A repository of state-of-the-art deep learning methods in computer vision
A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body
Model summary in PyTorch similar to `model.summary()` in Keras
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, …
Evaluation of the CNN design choices performance on ImageNet-2012.
Train AI models efficiently on medical images using any framework
Kaggle DSTL Satellite Imagery Feature Detection
Quickly comparing your image classification models with the state-of-the-art models (such as DenseNet, ResNet, ...)
Machine Learning Workflow, from Andrew Ng's lecture at Deep Learning Summer School 2016
Using neural networks to build an automatic number plate recognition system
Deep Reinforcement Learning library for humans
The "Python Machine Learning (1st edition)" book code repository and info resource
Preparation links and resources for system design questions