In this competition, you are provided with images of chemicals, with the objective of predicting the corresponding [International Chemical Identifier](https://en.wikipedia.org/wiki/International_Chemical_Identifier) (InChI) text string of the image. The images provided (both in the training data as well as the test data) may be rotated to different angles, be at various resolutions, and have different noise levels. 

**Note:** There are about 4m total images in this dataset. Unzipping the downloaded data will take a non-trivial amount of time. 

## Files

*   **train/** - the training images, arranged in a 3-level folder structure by `image_id`
*   **test/** - the test images, arranged in the same folder structure as `train/`
*   **train_labels.csv** - ground truth InChi labels for the training images
*   **sample_submission.csv** - a sample submission file in the correct format