ml-lab

auxiliary-deep-generative-models

Implementation of auxiliary deep generative models for semi-supervised learning

Awesome-Face-Forgery-Generation-and-Detection

A curated list of articles and codes related to face forgery generation and detection.

DeepVideoAnalytics

Analyze videos, perform detections, index frames & detected objects, search by examples

DRN-1

Code for "Learning Multiple Tasks with Deep Relationship Networks" NIPS 2017

home-platform

A Household multimodal environment (HoME) based on the SUNCG indoor scenes dataset

LLaMA-Adapter-2

Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

MobilePose-pytorch

Single Person Pose Estimation for Mobile Device

PointGrow

An autoregressive model for point cloud generation augmented with self-attention

pose-residual-network

Code for 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network' paper

pseudo-3d-residual-networks

Pseudo-3D Convolutional Residual Networks for Video Representation Learning

ml-lab/AdelaiDepth

This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.

ml-lab/FARM

:house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.

ml-lab/gpt-neox

An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hundreds of billions of parameters or larger.

ml-lab/agents-1

TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.

ml-lab/alphafold

Open source code for AlphaFold.

ml-lab/bayesian-algorithm-execution

Bayesian algorithm execution (BAX)

ml-lab/co3d

Tooling for the Common Objects In 3D dataset.

ml-lab/emacs-secondmate

An open-source, mini imitation of GitHub Copilot for Emacs.

ml-lab/gansformer

Generative Adversarial Transformers

ml-lab/Generalized-Smoothing-Framework

This is the released code for the following papers: A generalized framework for edge-preserving and structure-preserving image smoothing. Liu W, et al., TPAMI 2021, AAAI 2020

ml-lab/GFKD

The implementation for the work "Graph-Free Knowledge Distillation for Graph Neural Networks".

ml-lab/huggingpics

🤗🖼️ HuggingPics: Fine-tune Vision Transformers for anything using images found on the web.

ml-lab/kart

Distributed version-control for geospatial and tabular data

ml-lab/learnable-strf

Learnable STRF, from Riad et al. 2021 JASA

ml-lab/Learning_to_diversify

This is the official code repository for ICCV2021 'Learning to Diversify from Single Domain'.

ml-lab/mesh-transformer-jax

Model parallel transformers in JAX and Haiku

ml-lab/MetaDance

ml-lab/MusicTools

ml-lab/pandas_alive

Create stunning, animated visualisations with Pandas & Matplotlib as easy as calling `df.plot_animated()`

ml-lab/petastorm

Petastorm library enables single machine or distributed training and evaluation of deep learning models from datasets in Apache Parquet format. It supports ML frameworks such as Tensorflow, Pytorch, and PySpark and can be used from pure Python code.

ml-lab/PlaneTR3D

[ICCV'21] PlaneTR: Structure-Guided Transformers for 3D Plane Recovery

ml-lab/Real-ESRGAN

Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.

ml-lab/resurrect3d

Cultural Heritage 3D Rendering Platform

ml-lab/RetrieveInStyle

Official PyTorch implementation of Retrieve in Style: Unsupervised Facial Feature Transfer and Retrieval.

ml-lab/scenic

Scenic: A Jax Library for Computer Vision and Beyond

ml-lab/slp

Shell Language Processing (SLP). Pre-processing of sh/bash/zsh/.. commands for Machine Learning models.

ml-lab/TransGAN

[Preprint] "TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up", Yifan Jiang, Shiyu Chang, Zhangyang Wang

ml-lab/TransT

Transformer Tracking (CVPR2021)

ml-lab/tsai

Time series Timeseries Deep Learning Pytorch fastai - State-of-the-art Deep Learning with Time Series and Sequences in Pytorch / fastai

ml-lab/YOLOX

YOLOX is a high-performance anchor-free YOLO. Exceeding yolov3~v5 with ONNX, TensorRT, ncnn, and Openvino supported.