Dataset Description

 The dataset contains four directories: monet_tfrec, photo_tfrec, monet_jpg, and photo_jpg. The monet_tfrec and monet_jpg directories contain the same painting images, and the photo_tfrec and photo_jpg directories contain the same photos.

 We recommend using TFRecords as a Getting Started competition is a great way to become more familiar with a new data format, but JPEG images have also been provided.

 The monet directories contain Monet paintings. Use these images to train your model.

 The photo directories contain photos. Add Monet-style to these images and submit your generated jpeg images as a zip file. Other photos outside of this dataset can be transformed but keep your submission file limited to 10,000 images.

 Note: Monet-style art can be created from scratch using other GAN architectures like DCGAN. The submitted image files do not necessarily have to be transformed photos.

 Check out the CycleGAN dataset to experiment with the artistic style of other artists.

Files

• monet_jpg - 300 Monet paintings sized 256x256 in JPEG format
• monet_tfrec - 300 Monet paintings sized 256x256 in TFRecord format
• photo_jpg - 7028 photos sized 256x256 in JPEG format
• photo_tfrec - 7028 photos sized 256x256 in TFRecord format

Submission format

• Your kernel’s output must be called images.zip and contain 7,000-10,000 images sized 256x256.