Skip to content

A Python toolkit for evaluating the quality of classification models for tasks of Zero-Shot Learning (ZSL) including the models construction with different insides (e.g. miscellaneous NN architectures), procedure for training and saving models for further evaluation.

License

Notifications You must be signed in to change notification settings

ZSLresearch-team/ZeroShotEval

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

29 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ZeroShotEval

A Python toolkit for evaluating the quality of classification models for tasks of Zero-Shot Learning (ZSL) including the models construction with different insides (e.g. miscellaneous NN architectures), procedure for training and saving models for further evaluation.

Pipeline

zeroshoteval_pipeline

NOTE: in the figure above there are examples of Python scripts and its names. Please note that it is work names for visualizing the structure of the project.

Usage

Step 1: datasets loading

Go to scripts directory and run downloading scripts. Example:

cd ./scripts 
./cub_download.sh

All datasets are placed in data directory

About

A Python toolkit for evaluating the quality of classification models for tasks of Zero-Shot Learning (ZSL) including the models construction with different insides (e.g. miscellaneous NN architectures), procedure for training and saving models for further evaluation.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published