Giter VIP home page Giter VIP logo

lafantasy / fastaudiovisual Goto Github PK

View Code? Open in Web Editor NEW

This project forked from paolo626/fastaudiovisual

0.0 0.0 0.0 213.82 MB

When doing audio and video sentiment recognition, I found that a lot of code is duplicated, often a function in different time debugging for a long time, based on this problem, I want to manage all the previous work, organized into an open source library can be iterative. For their own use and others.

License: MIT License

Python 100.00%

fastaudiovisual's Introduction

FastAudioVisual license

Our project is developed here. The goal finish time is March 01, 2021

What is FastAudioVisual?

FastAudioVisual is a tool that allows us to develop and analyse research in the audiovisual domain. The framework of this model as follow: 在这里插入图片描述

As we can see that this project has five parts. Here is the detail of each part.

  1. DataRegular: It causes many questions due to different file structure in some research. In this work, we develop a series of functions to make your database regular with the next step. All of these funfunctions arested and regular by RAVDESS which is a big database in multimodal emotion recognition.

  2. FeatureExtract: Features extraction is important for model study. There are many features can be extracted for input. For audio, MFCC, FBank, crossing-zero rate and soon on can be used. For visual, gray, RGB, optical flow diagram can be used. In this part, we will build some API to extract these features.

  3. SampleModel: With the develop of hardwares, deep learning has got siginificant improvement in every area. Many area has been regular by deep learning. Therefore, we collect some classical model for basic research. This part will make you have a enough evaluate and experiment. (In the beginning, I struggled to choose Pytorch and fastai).

  4. ModelDesign: In this part, we focus on audiovisual fusion method and model design for audiovisual other domain( including loss , framework, other trick.). It collect some research work and code. Also, we can replace simplemodel into this part. Making the result is better.

  5. Analysis: Based on above parts, we will using some tool to analysis the result of this experiment. Such as confusion matrix, CAM, feature distrbution.

  6. Test: Some demo for using this project.

  7. Others: It includes some paper or blog for this area.

In general, All of these design is for developing your audiovisual research fastly by this ttool!

Develop and Iteration

3. 功能内容与具体

4. 后期维护与迭代

Installation

You can install, upgrade, uninstall count-line with these commands(without $):

$ pip install FastAudioVisual
$ pip install --upgrade FastAudioVisual
$ pip unstall FastAudioVisual

Help

usage: line.py [-h] [-s SUFFIX | -f FILTER] [-d]

count the amount of lines and files under the current directory

optional arguments:
  -h, --help            show this help message and exit
  -s SUFFIX, --suffix SUFFIX
                        count by suffix file name, format: .suffix1.suffix2...
                        e.g: .cpp.py (without space)
  -f FILTER, --filter FILTER
                        count without filter name, format: .suffix1.suffix2...
                        e.g: .cpp.py (without space)
  -d, --detail          show detail results

Examples

  1. Count all files under the current directory:
$ line
Search in /Users/macbook/Desktop/Examples1/
file count: 4
line count: 373
  1. Count all files under the current directory with detail results:
$ line -d
Search in /Users/macbook/Desktop/Examples2/

		========================================
		文件后缀名	文件数		总行数
		

		   .py		5		397
		

		   .cpp		240		11346
		

		总文件数: 245	总行数: 11743
		========================================
		

  1. Count specified files under the current directory, using -s to pass suffix as parameters, if there are more than one parameter, don't have space, for example, count cpp files and python files:
$ line -s .cpp.py
Search in /Users/macbook/Desktop/Examples3/
file count: 3
line count: 243
$ line -s .cpp.py -d
Search in /Users/macbook/Desktop/Examples3/

		========================================
		文件后缀名	文件数		总行数
		

		   .py		5		397
		

		   .cpp		240		11346
		

		总文件数: 245	总行数: 11743
		========================================
		
  1. Count files under the current directory with filter:
$ line -f .py -d
Search in /Users/macbook/Desktop/Examples4/

		========================================
		文件后缀名	文件数		总行数
		

		   .cpp		240		11346
		

		总文件数: 240	总行数: 11528
		========================================
$ line -d
Search in /Users/macbook/Desktop/Examples4/

		========================================
		文件后缀名	文件数		总行数
		

		   .py		5		397
		

		   .cpp		240		11346
		

		总文件数: 245	总行数: 11743
		========================================

		

fastaudiovisual's People

Contributors

paolo626 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.