Petals to the Metal - Flower Classification on TPU

Who this competition fits

Advanced practitioners with experience in general machine learning. Requires strong technical foundations and comfort with complex ML pipelines.

What this competition gives you

There is a baseline you can run as-is — starting from it is usually far faster than building from scratch.

• BaselineForkable TensorFlow 2.2 flower-classification starter notebook
• TutorialVideo showing how to get started with TPUs
• TutorialStep-by-step first-submission tutorial
• DataCompetition flower-image dataset in TFRecord format
• TutorialGetting Started notebook for loading and using data
• TutorialLearn exercise for loading and using TFRecord data
• TutorialTPU documentation
• Support channelCompetition forum for questions and troubleshooting
• MentoringKaggle Data Scientists actively answer competition questions
• TutorialYouTube playlist introducing TPUs
• TutorialTPU documentation and resources

From registration to a first submission

1. 01

   Python

2. 02

   scikit-learn or similar ML library

3. 03

   data analysis with pandas

Before you commit: Requires solid machine learning fundamentals and good experimental methodology. The competitive landscape is strong, with many experienced teams.