RobustBench: a standardized adversarial robustness benchmark [arXiv, Oct 2020]
NeurIPS 2020 Spotlight, trains fast as Adam, generalizes well as SGD, and is stable to train GANs.
pystiche (pronounced /ˈpaɪˈstiʃ/ ) is a framework for Neural Style Transfer (NST) built upon PyTorch.
Retinal imaging serves as a valuable tool for diagnosis of various diseases.
The Cross-lingual Choice of Plausible Alternatives dataset is a benchmark to evaluate the ability of machine learning models to transfer commonsense reasoning across languages.
D2Det using mmdetection v2.1, supporting Objects365 and LVIS
ReDWeb-S: a large-scale challenging dataset for RGB-D Salient Object Detection.
A GUI for Nvidia's GauGAN/SPADE like shown in the tech demo.
SMARTS (Scalable Multi-Agent RL Training School) is a simulaton platform for reinforcement learning and multi-agent research on autonomous driving.
tract is a Neural Network inference toolkit. It can read Tensorflow 1, ONNX or NNEF, optimize them and run data through them.
A docker based low-latency deep learning library and inference server written in C++11 using the PyTorch C++ frontend.
The Fusion 360 Gallery Dataset contains rich 2D and 3D geometry data derived from parametric CAD models.
The time series forecasting package for the tidymodels ecosystem.
High Performance Tensorflow Data Pipeline with State of Art Augmentations and low level optimizations.
Photo-realistic free-viewpoint rendering of real-world scenes using classical computer graphics techniques is a challenging problem because it requires the difficult step of capturing detailed appearance and geometry models.
LI-Calib is a toolkit for calibrating the 6DoF rigid transformation and the time offset between a 3D LiDAR and an IMU.
A Language Classifier powered by Recurrent Neural Network(RNN) implemented in Python without AI libraries.
This is a PyTorch implementation of our paper Multi-modal Dense Video Captioning (CVPR Workshops 2020).
This project is a PyTorch implementation of Learning to Coordinate Manipulation Skills via Skill Behavior Diversification, which is published in ICLR 2020.
Source code for some of the results shown in the paper "Segment Tracing Using Local Lipschitz Bounds" published in CGF in 2020 and presented at Eurographics 2020.
unofficial implement of DMFN.
robot Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness. EMNLP, 2020
A Generative Adversarial Network implementation that generates Sharingans. This was trained on Google Colab with 3000 epochs and it took about 10 minutes to train.
The image dataset tool (IDT) is a CLI app developed to make it easier and faster to create image datasets to be used for deep learning.
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch.