Our project is developed here. The goal finish time is March 01, 2021
What is FastAudioVisual?
As we can see that this project has five parts. Here is the detail of each part.
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.
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.
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).
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.
Analysis: Based on above parts, we will using some tool to analysis the result of this experiment. Such as confusion matrix, CAM, feature distrbution.
Test: Some demo for using this project.
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
You can install, upgrade, uninstall count-line with these commands(without $):
$ pip install FastAudioVisual $ pip install --upgrade FastAudioVisual $ pip unstall FastAudioVisual
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
- Count all files under the current directory:
$ line Search in /Users/macbook/Desktop/Examples1/ file count: 4 line count: 373
- 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 ========================================
- 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 ========================================
- 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 ========================================