PyTorch training code and pretrained models for CATR (CAption TRansformer).
This repo is an optimized CUDA version of FIt-SNE algorithm with associated python modules.
TODS is a full-stack automated machine learning system for outlier detection on multivariate time-series data.
With Qlib, you can easily try your ideas to create better Quant investment strategies.
Everybody wants to learn good representations of data. However, defining precisely what we mean by a good representation can be tricky.
Full knowledge and control of the train state.
This is the code for paper "Siamese Dense Network for Reflection Removal with Flash and No-flash Image Pairs".
Mathematical Modeling for Optimization and Machine Learning.
Darkshot is a scraper tool on steroids, to analyze all of the +2 Billions pictures publicly available on Lightshot.
Self-supervised Single-view 3D Reconstruction.
This is the offical implementation of paper Quasi-Dense Instance Similarity learning.
This repository contains slides, notebooks, and datasets for the Machine Learning University (MLU) Accelerated Tabular Data class.
Official repository for ECCV 2020 paper "DeepLandscape: Adversarial Modeling of Landscape Videos"
StyleGAN-based predictor of children's faces from photographs of theoretical parents.
code for ECCV-2020 Self-supervised Video Representation Learning by Pace Prediction
Object tracking implemented with YOLOv4, DeepSort, and TensorFlow.
graftr: an interactive shell to view and edit PyTorch checkpoints.
Official Keras Implementation of ChromaGAN: Adversarial Picture Colorization with Semantic Class Distribution
Simple dynamic library for video sentiment recognition.
Super Fast and Accurate 3D Object Detection based on 3D LiDAR Point Clouds (The PyTorch implementation).
Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networks
Official implementation of "VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment"
Demonstration using Google Colab to show how U-2-NET can be used for Background Removal, Boudning Box Creation and Salient Feature Highlighting
Virtual Clothing Try-on with Deep Learning. PyTorch reproduction of SwapNet by Raj et al.
This is a pytorch-based implementation for paper ContourNet (CVPR2020).