Abstract: The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling.
Build neat pipelines with the right abstractions to do AutoML. Let your pipeline steps have hyperparameter spaces.
MovingPandas implements a Trajectory class and corresponding methods based on GeoPandas.
Code for paper: "Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models".
We propose AugMix, a data processing technique that mixes augmented images and enforces consistent embeddings of the augmented images, which results in increased robustness and improved uncertainty calibration.
Authoring adaptive color palettes for generating color based on a desired contrast ratio.
Pytorch implementation of Learning Rate Dropout.
This repo contains a PyTorch implementation of learning rate dropout from the paper "Learning Rate Dropout" by Lin et al.
Convert video to 3D pose in one-key.
Using Machine Learning to learn how to Compress.
Learn how to use PyTorch to solve some common NLP problems with deep learning. View these notebooks on nbviewer.
This is my school project. It focuses on Reinforcement Learning for personalized news recommendation.
a simple PlantsVsZombies game.
TorchSat is an open-source deep learning framework for satellite imagery analysis based on PyTorch.
Classy Vision is a new end-to-end, PyTorch-based framework for large-scale training of state-of-the-art image and video classification models.
ToCenter is a video game written in Rust using the ggez engine and the ECS library. This game is my hobby project and not considerate a best example use ggez.
In recent years, natural language processing (NLP) has seen quick growth in quality and usability, and this has helped to drive business adoption of artificial intelligence (AI) solutions.
This repository is to do car recognition by fine-tuning ResNet-152 with Cars Dataset from Stanford.
Accelerated Text helps you automatically generate natural language descriptions of your data varying in wording and structure.
Apache TVM (incubating) is a compiler stack for deep learning systems.
Deep Learning Framework for various Image Recognition Tasks. Photogrammetry and Robotics Lab, University of Bonn.
NER markup visualization for Jupyter Notebook.
An Tensorflow implementation of PersonLab for Multi-Person Pose Estimation and Instance Segmentation.
The repository contains the code of the recent research advances in Shannon.AI.
Proposal-generation, Refinement and Merging for Video Object Segmentation.