Skip to content

ShayanRamazi/feature-Generating-Networks-for-ZeroShotLearning

Repository files navigation

Feature Generating Networks for ZSL in Keras

N|Solid

keras implementation of paper: Feature Generating Networks for Zero-Shot Learning

Datasets

Original files

Download: data This dataset provides a platform to benchmark transfer-learning algorithms, in particular, attribute base classification and zero-shot learning. It can act as a drop-in replacement to the original Animals with Attributes (AwA) dataset, as it has the same class structure and almost the same characteristics. In addition, on this website, you will find CUB, SUN, FLO.

Dataset in H5File

In order to run our experiments, and facilitate visualization of the dataset, we introduce the GZSL datasets in H5file format. You can download the datasets CUB, SUN, FLO, and AWA1 in the h5file format, which can be downloaded dataset.zip (~3GB in zip file).

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages