# Flower Classification with TPUs — Data

来源：https://www.kaggle.com/competitions/flower-classification-with-tpus/data

采集时间：2026-10-19T06:32:46Z

In this competition we're classifying 104 types of flowers based on their images drawn from five different public datasets. Some classes are very narrow, containing only a particular sub-type of flower (e.g. pink primroses) while other classes contain many sub-types (e.g. wild roses).

## Files
This competition is different in that images are provided in TFRecord format. The TFRecord format is a container format frequently used in Tensorflow to group and shard data data files for optimal training performace.
Each file contains the `id`, `label` (the class of the sample, for training data) and `img` (the actual pixels in array form) information for many images. 
Please see our getting [started notebook](https://www.kaggle.com/mgornergoogle/getting-started-with-100-flowers-on-tpu/) for notes on how to load and use them! Additional information is available in the [TPU documentation](https://www.kaggle.com/docs/tpu).

*   **train/\*.tfrec** - training samples, including labels.
*   **val/\*.tfrec** - pre-split training samples w/ labels intended to help with checking your model's performance on TPU. The split was stratified across labels.
*   **test/\*.tfrec** - samples without labels - you'll be predicting what classes of flowers these fall into.
*   **sample_submission.csv** - a sample submission file in the correct format

  `id` - a unique ID for each sample.

  `label` - (in training data) the class of flower represented by the sample