Python Mixed-precision-training Resources

FFRecord The FFRecord format is a simple format for storing a sequence of binary records developed by HFAiLab, which supports random access and Linux

ROSITA News & Updates (24/08/2021) Release the demo to perform fine-grained semantic alignments using the pretrained ROSITA model. (15/08/2021) Releas

Selene is a Python library and command line interface for training deep neural networks from biological sequence data such as genomes.

RoSTER The source code used for Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training, p

Real-ESRGAN Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data Ported from https://github.com/xinntao/Real-ESRGAN Depend

Pre-trained (foundation) models across tasks (understanding, generation and translation), languages (100+ languages), and modalities (language, image, audio, vision + language, audio + language, etc.)

近年来，图计算在搜索、推荐和风控等场景中获得显著的效果，但也面临超大规模异构图训练，与现有的深度学习框架Tensorflow和PyTorch结合等难题。 Galileo（伽利略）是一个图深度学习框架，具备超大规模、易使用、易扩展、高性能、双后端等优点，旨在解决超大规模图算法在工业级场景的落地难题，提

Transformer Captioning This repository contains the code for Transformer-based image captioning. Based on meshed-memory-transformer, we further optimi

The code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task —— Next Sentence Prediction"

Speech Separation The simple project to separate mixed voice (2 clean voices) to 2 separate voices. Result Example (Clisk to hear the voices): mix ||

End-to-end neural table-text understanding models.

Generate text line images for training deep learning OCR model (e.g. CRNN)

Model Training as a CI/CD System This project demonstrates the machine model training as a CI/CD system in GCP platform. You will see more detailed wo

COTREC Codes for CIKM'21 paper 'Self-Supervised Graph Co-Training for Session-based Recommendation'. Requirements: Python 3.7, Pytorch 1.6.0 Best Hype

TAPEX: Table Pre-training via Learning a Neural SQL Executor The official repository which contains the code and pre-trained models for our paper TAPE

Megatron (1 and 2) is a large, powerful transformer developed by the Applied Deep Learning Research team at NVIDIA.

WGAN-GP An pytorch implementation of Paper "Improved Training of Wasserstein GANs". Prerequisites Python, NumPy, SciPy, Matplotlib A recent NVIDIA GPU

Train longer, generalize better - Big batch training This is a code repository used to generate the results appearing in "Train longer, generalize bet

FreezeOut A simple technique to accelerate neural net training by progressively freezing layers. This repository contains code for the extended abstra

forward-thinking-pytorch Pytorch implementation of Forward Thinking: Building and Training Neural Networks One Layer at a Time Requirements Python 2.7

Alias-Free GAN An unofficial version of Alias-Free Generative Adversarial Networks (https://arxiv.org/abs/2106.12423). This repository was heavily bas

Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study Codes for [Preprint] Bag of Tricks for Training Deeper Graph

Flood Detection Challenge This repository contains code for our submission to the ETCI 2021 Competition on Flood Detection (Winning Solution #2). Acco

ST++ This is the official PyTorch implementation of our paper: ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation. Lihe Ya

Multi-Modal Self-Supervision using GDT and StiCa This is an official pytorch implementation of papers: Multi-modal Self-Supervision from Generalized D

DepthNet training on Still Box Project page This code can replicate the results of our paper that was published in UAVg-17. If you use this repo in yo

The DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a conditional cross-attention mechanism for fast DETR training. Our approach is motivated by that the cross-attention in DETR relies highly on the content embeddings and that the spatial embeddings make minor contributions, increasing the need for high-quality content embeddings and thus increasing the training difficulty.

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation This is a pytorch project for the paper Dynamic Divide-and-Conquer Ad

An Image Captioning codebase This is a codebase for image captioning research. It supports: Self critical training from Self-critical Sequence Trainin

This repo is the official implementation of our paper "Instance Adaptive Self-training for Unsupervised Domain Adaptation". The purpose of this repo is to better communicate with you and respond to your questions. This repo is almost the same with Another-Version, and you can also refer to that version.

What is this fork of Megatron-LM and Megatron-DeepSpeed This is a detached fork of https://github.com/microsoft/Megatron-DeepSpeed, which in itself is

An Effective Loss Function for Generating 3D Models from Single 2D Image without Rendering Papers with code | Paper Nikola Zubić Pietro Lio University

Kaleido-BERT: Vision-Language Pre-training on Fashion Domain Mingchen Zhuge*, Dehong Gao*, Deng-Ping Fan#, Linbo Jin, Ben Chen, Haoming Zhou, Minghui

Updates (2020/06/21) Code of PVTv2 is released! PVTv2 largely improves PVTv1 and works better than Swin Transformer with ImageNet-1K pre-training. Pyr

LightSeq: A High Performance Library for Sequence Processing and Generation

ODE GAN (Prototype) in PyTorch Partial implementation of ODE-GAN technique from the paper Training Generative Adversarial Networks by Solving Ordinary

GMPQ: Generalizable Mixed-Precision Quantization via Attribution Rank Preservation This is the pytorch implementation for the paper: Generalizable Mix

DenseClus is a Python module for clustering mixed type data using UMAP and HDBSCAN. Allowing for both categorical and numerical data, DenseClus makes it possible to incorporate all features in clustering.

ManiSkill-Learn ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge, a large-scale learning-from-dem

SemCo The official pytorch implementation of the paper All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training

Epistemic Neural Networks A library for uncertainty representation and training in neural networks. Introduction Many applications in deep learning re

背景 安装教程 快速上手 （一）预训练模型 （二）机器翻译 （三）文本分类 TenTrans 进阶 1. 多语言机器翻译 2. 跨语言预训练 背景 TrenTrans是一个统一的端到端的多语言多任务预训练平台，支持多种预训练方式，以及序列生成和自然语言理解任务。 安装教程 git clone git

🤖 Interactive Machine Learning experiments: 🏋️models training + 🎨models demo

MASS: Masked Sequence to Sequence Pre-training for Language Generation

In-Place Activated BatchNorm In-Place Activated BatchNorm for Memory-Optimized Training of DNNs In-Place Activated BatchNorm (InPlace-ABN) is a novel

Proximal Backpropagation Proximal Backpropagation (ProxProp) is a neural network training algorithm that takes implicit instead of explicit gradient s

Use this instead: https://github.com/facebookresearch/maskrcnn-benchmark A Pytorch Implementation of Detectron Example output of e2e_mask_rcnn-R-101-F

GAN stability This repository contains the experiments in the supplementary material for the paper Which Training Methods for GANs do actually Converg

Bridging Multi-Task Learning and Meta-Learning Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Trainin

Deduplicating Training Data Makes Language Models Better This repository contains code to deduplicate language model datasets as descrbed in the paper

This repository is a toolkit to do machine learning for programming languages. It implements tokenization, dataset preprocessing, model training and m

ViTGAN: Training GANs with Vision Transformers A PyTorch implementation of ViTGAN based on paper ViTGAN: Training GANs with Vision Transformers. Refer

DiffAI v3 DiffAI is a system for training neural networks to be provably robust and for proving that they are robust. The system was developed for the

ClusterGCN ⠀⠀ A PyTorch implementation of "Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks" (KDD 2019). A

Self-training for Few-shot Transfer Across Extreme Task Differences (STARTUP) Introduction This repo contains the official implementation of the follo

Adam-NSCL This is a PyTorch implementation of Adam-NSCL algorithm for continual learning from our CVPR2021 (oral) paper: Title: Training Networks in N

StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking Datasets You can download datasets that have been pre-pr

MidiBERT-Piano Authors: Yi-Hui (Sophia) Chou, I-Chun (Bronwin) Chen Introduction This is the official repository for the paper, MidiBERT-Piano: Large-

AlphaNet: Improved Training of Supernet with Alpha-Divergence This repository contains our PyTorch training code, evaluation code and pretrained model

Accelerate PyTorch models with ONNX Runtime

Решения и подсказки к тренировке по алгоритмам от Яндекса Что есть внутри Решения с подсказками и комментариями; рекомендую сначала смотреть md файл п

The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.

HyperPose is a library for building high-performance custom pose estimation applications.

Prefix date parser This is a helper class to parse dates with varied degrees of precision. For example, a data source might state a date as 2001, 2001

Piotr: Pythonic IoT exploitation and Research Introduction to Piotr Piotr is an emulation helper for Qemu that provides a convenient way to create, sh

Chasing Sparsity in Vision Transformers: An End-to-End Exploration Codes for [Preprint] Chasing Sparsity in Vision Transformers: An End-to-End Explora

WAGMA-SGD is a decentralized asynchronous SGD based on wait-avoiding group model averaging. The synchronization is relaxed by making the collectives externally-triggerable, namely, a collective can be initiated without requiring that all the processes enter it. It partially reduces the data within non-overlapping groups of process, improving the parallel scalability.

Bagua is a flexible and performant distributed training algorithm development framework.

This software automatically sends you emails to notify you of the latest progress of your deep learning programs.

Spectral Tensor Train Parameterization of Deep Learning Layers This repository is the official implementation of our AISTATS 2021 paper titled "Spectr

Balancing Training for Multilingual Neural Machine Translation Implementation of the paper Balancing Training for Multilingual Neural Machine Translat

flax-sentence-embeddings This repository will be used to share code for the Flax / JAX community event to train sentence embeddings on 1B+ training pa

PLOME:Pre-training with Misspelled Knowledge for Chinese Spelling Correction (ACL2021) This repository provides the code and data of the work in ACL20

KGI (Knowledge Graph Induction) for slot filling This is the code for our KILT leaderboard submission to the T-REx and zsRE tasks. It includes code fo

PGT Code for paper PGT: A Progressive Method for Training Models on Long Videos. Install Run pip install -r requirements.txt. Run python setup.py buil

TransFill-Reference-Inpainting This is the official repo for TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transf

BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data This repository provides the implementation details for

Efficient implementation of YOLOV5 in TensorFlow2

EdMIPS is an efficient algorithm to search the optimal mixed-precision neural network directly without proxy task on ImageNet given computation budgets. It can be applied to many popular network architectures, including ResNet, GoogLeNet, and Inception-V3.

The inductive bias of a neural network is largely determined by the architecture and the training algorithm. To achieve good generalization, how to effectively train a neural network is of great importance. We propose a novel orthogonal over-parameterized training (OPT) framework that can provably minimize the hyperspherical energy which characterizes the diversity of neurons on a hypersphere. See our previous work -- MHE for an in-depth introduction.

ncnnqat ncnnqat is a quantize aware training package for NCNN on pytorch. Table of Contents ncnnqat Table of Contents Installation Usage Code Examples

TAP: Text-Aware Pre-training TAP: Text-Aware Pre-training for Text-VQA and Text-Caption by Zhengyuan Yang, Yijuan Lu, Jianfeng Wang, Xi Yin, Dinei Flo

One Thing One Click One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation (CVPR2021) Code for the paper One Thi

UC2 UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training Mingyang Zhou, Luowei Zhou, Shuohang Wang, Yu Cheng, Linjie Li, Zhou Yu,

SelfText Beyond Polygon: Unconstrained Text Detection with Box Supervisionand Dynamic Self-Training Introduction This is a PyTorch implementation of "

AdamBNN This is the pytorch implementation of our paper "How Do Adam and Training Strategies Help BNNs Optimization?", published in ICML 2021. In this

This is a release of our VIMPAC paper to illustrate the implementations. The pretrained checkpoints and scripts will be soon open-sourced in HuggingFace transformers.

An implementation of a floating-point binary fractions class and module in Python. Work with binary fractions and binary floats with ease!

Secure Distributed Training at Scale This repository contains the implementation of experiments from the paper "Secure Distributed Training at Scale"

DistML is a Ray extension library to support large-scale distributed ML training on heterogeneous multi-node multi-GPU clusters

ASPset-510 (Australian Sports Pose Dataset) is a large-scale video dataset for the training and evaluation of 3D human pose estimation models. It contains 17 different amateur subjects performing 30 sports-related actions each, for a total of 510 action clips.

ASPset-510 ASPset-510 (Australian Sports Pose Dataset) is a large-scale video dataset for the training and evaluation of 3D human pose estimation mode

Habitat: A Runtime-Based Computational Performance Predictor for Deep Neural Network Training Habitat is a tool that predicts a deep neural network's

文字是人类用以记录和表达的最基本工具，也是信息传播的重要媒介。透过文字与符号，我们可以追寻人类文明的起源，可以传播知识与经验，读懂文字是认识与了解的第一步。对于人工智能而言，它的核心问题之一就是认知，而认知的核心则是语义理解。

SnakeOfLife Snake game mixed with Conway's Game of Life The rules are the same than a normal snake game but you have to avoid cells created by Conway'

This repository is the official PyTorch implementation of SAINT. Find the paper on arxiv SAINT: Improved Neural Networks for Tabular Data via Row Atte

Training data extraction from GPT-2 This repository contains code for extracting training data from GPT-2, following the approach outlined in the foll

Degree-Quant This repo provides a clean re-implementation of the code associated with the paper Degree-Quant: Quantization-Aware Training for Graph Ne

The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models Codes for this paper The Lottery Tickets Hypo

A no-BS, dead-simple training visualizer for tf-keras TrainingDashboard Plot inter-epoch and intra-epoch loss and metrics within a jupyter notebook wi