We have used Flickr8k Dataset for training and testing.
The Dataset comprises 2 directories:
- Flickr8k_Dataset: Contains 8092 photographs in JPEG format.
- Flickr8k_text: Contains a number of files containing different sources of descriptions for the photographs.
The dataset has a pre-defined training dataset (6,000 images), development dataset (1,000 images), and test dataset (1,000 images).
To Download the dataset use this link.
A big shout out to Jason Brownlee for providing us with so many datasets at one place.