Skip to content

Releases: lRomul/ball-action-spotting

Trained models

19 Jun 09:00
Compare
Choose a tag to compare

What's new

  • Link to download trained models and predictions
  • Add requirements.txt file

Initial release

17 Jun 00:15
Compare
Choose a tag to compare

Solution

The solution includes an efficient model architecture and a multi-stage training pipeline for spotting the instances of passes and drives occurring in soccer videos.

Key points:

  • Efficient model architecture for extracting information from video data
  • Multi-stage training pipeline (transfer learning, fine-tuning with long sequences)
  • Fast video loading pipeline for training (GPU decoding, no need for preprocessing with extracting images)