# I’m Something of a Painter Myself — Data

来源：https://www.kaggle.com/competitions/gan-getting-started/data

采集时间：2026-10-24T16:03:59Z

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](https://github.com/junyanz/CycleGAN) 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.