Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once; across one or thousands of GPUs.

A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")

Multithreaded Python without the GIL

Supplementary material of "Deep Unsupervised Drum Transcription", ISMIR 2019

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Debugging, monitoring and visualization for Python Machine Learning and Data Science

PyTorch original implementation of Cross-lingual Language Model Pretraining.

Python package built to ease deep learning on graph, on top of existing DL frameworks.

Visualisation tool for CNNs in pytorch

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Code for visualizing the loss landscape of neural nets

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding a…

Playing around with JointVAE implementation - WIP

Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101

Model analyzer in PyTorch

Transpile trained scikit-learn estimators to C, Java, JavaScript and others.

Demonstration of using Caffe2 inside an Android application.

The fundamental package for scientific computing with Python.

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Open standard for machine learning interoperability

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

A command-line and interactive shell framework.

An open-source C++ library developed and used at Facebook.

Deep Learning Projects that Build Themselves

PyTorch implementations of algorithms for density estimation

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

[ECCV 2018]: T2Net: Synthetic-to-Realistic Translation for Depth Estimation Tasks

NYU Deep Learning Spring 2020

ICRA 2018 "Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image" (PyTorch Implementation)

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas lik…