The Flickr30k dataset has become a standard benchmark for sentence-based image description.

This is a very high quality dataset of playing card images. All images are 224 X 224 X 3 in jpg format.

The dataset facilitates new benchmarks for textual entity localization in images, supported by a robust baseline that includes image-text embedding, common object detectors, a color classifier, and a preference for larger objects.

Unlock the potential of generative AI with the Prompt2Image dataset, featuring prompts paired with images generated by state-of-the-art model.

There are several images in different poses or with different environments for each Minifigure in the dataset. You can use this dataset for the image classification tasks or try to create more interesting things.

Images were gathered from Google searches and downloaded using app ‘download all images’ . I highly recommend this app as it is very fast and returns a zip file with the images which you can then unzip to a specific directory.

I planned to create a fish image recognizer that mostly get sold in bengali fish markets. So, I downloaded the data using duckdukgo search and prepared the data for 20 different types of fishes.

The “Indian-Birds-Species-Image-Classification” consists of 25 bird species found in India, including Asian Green Bee-eater, Brown-Headed Barbet.

Join the community of businesses and professionals who have enhanced their images with Image Super Resolution.