一个多模态内容理解算法框架,其中包含数据处理、预训练模型、常见模型以及模型加速等模块。

Related tags

Deep LearningLichee
Overview

Overview

框架简介

方便使用,支持多模态,多任务的统一训练框架

能力列表:

  • bert + 分类任务
  • 自定义任务训练(插件注册)

框架设计

框架采用分层的思想组织模型训练流程。

  • DATA 层负责读取用户数据,根据 field 管理数据。
  • Parser 层负责转换原始数据为模型的输入。
  • MODEL 层为模型层,具体由表示层(REPRESENTATION)和任务层(TASK)组成。
    • 表示层用于抽取数据的高维特征,框架里内置了一些成熟实现(包括bert、NeXtVLAD等)。
    • 任务层用于拟合具体的训练任务,框架里提供一些默认实现(包括分类任务等),用户也可以根据训练任务,自定义任务模型。
    • 任务层可用于实现多任务训练。
  • 框架通过配置文件组合 DATA、Parser、MODEL、Optimizer、Scheduler,构建具体的训练流程。
  • 框架还内置了成熟的组件模块(Module),包括 Metrics、Loss、Layer 等,供用户选择使用。

详细可参考文档

框架安装

参考文档

使用说明

cd examples/base_bert_cls_mac
sh train.sh
sh eval.sh
sh predict.sh

模型训练任务被拆分为三步,每个步骤可以独立运行:

任务执行均依赖配置文件,详细介绍可参考文档

若框架默认实现无法满足需求,也可以实现自定义插件,详细介绍可参考文档

Contributing

如果你有好的意见或建议,欢迎给我们提 Issues 或 Pull Requests,为蓝鲸开源社区贡献力量。关于标准运维分支管理、Issue 以及 PR 规范, 请阅读 Contributing Guide

Owner
Tencent
Tencent
Official pytorch code for "APP: Anytime Progressive Pruning"

APP: Anytime Progressive Pruning Diganta Misra1,2,3, Bharat Runwal2,4, Tianlong Chen5, Zhangyang Wang5, Irina Rish1,3 1 Mila - Quebec AI Institute,2 L

Landskape AI 12 Nov 22, 2022
Apply Graph Self-Supervised Learning methods to graph-level task(TUDataset, MolculeNet Datset)

Graphlevel-SSL Overview Apply Graph Self-Supervised Learning methods to graph-level task(TUDataset, MolculeNet Dataset). It is unified framework to co

JunSeok 8 Oct 15, 2021
Deep learning operations reinvented (for pytorch, tensorflow, jax and others)

This video in better quality. einops Flexible and powerful tensor operations for readable and reliable code. Supports numpy, pytorch, tensorflow, and

Alex Rogozhnikov 6.2k Jan 01, 2023
Generates all variables from your .tf files into a variables.tf file.

tfvg Generates all variables from your .tf files into a variables.tf file. It searches for every var.variable_name in your .tf files and generates a v

1 Dec 01, 2022
Implementation of MA-Trace - a general-purpose multi-agent RL algorithm for cooperative environments.

Off-Policy Correction For Multi-Agent Reinforcement Learning This repository is the official implementation of Off-Policy Correction For Multi-Agent R

4 Aug 18, 2022
This repository is for our EMNLP 2021 paper "Automated Generation of Accurate & Fluent Medical X-ray Reports"

Introduction: X-Ray Report Generation This repository is for our EMNLP 2021 paper "Automated Generation of Accurate & Fluent Medical X-ray Reports". O

no name 36 Dec 16, 2022
PyTorch version repo for CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes

Study-CSRNet-pytorch This is the PyTorch version repo for CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes

0 Mar 01, 2022
Official code release for: EditGAN: High-Precision Semantic Image Editing

Official code release for: EditGAN: High-Precision Semantic Image Editing

565 Jan 05, 2023
Machine Learning toolbox for Humans

Reproducible Experiment Platform (REP) REP is ipython-based environment for conducting data-driven research in a consistent and reproducible way. Main

Yandex 662 Nov 20, 2022
Code for Talking Face Generation by Adversarially Disentangled Audio-Visual Representation (AAAI 2019)

Talking Face Generation by Adversarially Disentangled Audio-Visual Representation (AAAI 2019) We propose Disentangled Audio-Visual System (DAVS) to ad

Hang_Zhou 750 Dec 23, 2022
Distributing Deep Learning Hyperparameter Tuning for 3D Medical Image Segmentation

DistMIS Distributing Deep Learning Hyperparameter Tuning for 3D Medical Image Segmentation. DistriMIS Distributing Deep Learning Hyperparameter Tuning

HiEST 2 Sep 09, 2022
A rule learning algorithm for the deduction of syndrome definitions from time series data.

README This project provides a rule learning algorithm for the deduction of syndrome definitions from time series data. Large parts of the algorithm a

0 Sep 24, 2021
[CVPR2021] The source code for our paper 《Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning》.

TBE The source code for our paper "Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Le

Jinpeng Wang 150 Dec 28, 2022
FAST-RIR: FAST NEURAL DIFFUSE ROOM IMPULSE RESPONSE GENERATOR

This is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment.

Anton Jeran Ratnarajah 89 Dec 22, 2022
Pytorch implementation of Generative Models as Distributions of Functions 🌿

Generative Models as Distributions of Functions This repo contains code to reproduce all experiments in Generative Models as Distributions of Function

Emilien Dupont 117 Dec 29, 2022
Code for "Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification", ECCV 2020 Spotlight

Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification Implementation of "Learning From Multiple Experts: Se

27 Nov 05, 2022
Code for paper: Towards Tokenized Human Dynamics Representation

Video Tokneization Codebase for video tokenization, based on our paper Towards Tokenized Human Dynamics Representation. Prerequisites (tested under Py

Kenneth Li 20 May 31, 2022
PyTorch implementation of the paper: "Preference-Adaptive Meta-Learning for Cold-Start Recommendation", IJCAI, 2021.

PAML PyTorch implementation of the paper: "Preference-Adaptive Meta-Learning for Cold-Start Recommendation", IJCAI, 2021. (Continuously updating ) Int

15 Nov 18, 2022
A Moonraker plug-in for real-time compensation of frame thermal expansion

Frame Expansion Compensation A Moonraker plug-in for real-time compensation of frame thermal expansion. Installation Credit to protoloft, from whom I

58 Jan 02, 2023
a reccurrent neural netowrk that when trained on a peice of text and fed a starting prompt will write its on 250 character text using LSTM layers

RNN-Playwrite a reccurrent neural netowrk that when trained on a peice of text and fed a starting prompt will write its on 250 character text using LS

Arno Barton 1 Oct 29, 2021