TTNet-Real-time-Analysis-System-for-Table-Tennis-Pytorch
torchio
| TTNet-Real-time-Analysis-System-for-Table-Tennis-Pytorch | torchio | |
|---|---|---|
| 2 | 2 | |
| 531 | 1,954 | |
| - | - | |
| 0.0 | 8.2 | |
| over 1 year ago | 15 days ago | |
| Python | Python | |
| - | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
TTNet-Real-time-Analysis-System-for-Table-Tennis-Pytorch
-
Good cameras for computer vision applied to tennis
I'll consider using two cameras, I figured one was enough because this paper gets good results with just that and was planning to use the same/similar network to get the same/similar results but applied to a different sport.
-
Deep Learning and Tennis Video annotation
Thanks - there are two models for ball tracking, first one is "coarse" and looks for the approximate position of the ball (using resized image) and the second one is updating coarse coordinates - and looks only at a patch of a high res image. It helped a lot and based on https://github.com/maudzung/TTNet-Real-time-Analysis-System-for-Table-Tennis-Pytorch
torchio
-
[P] TorchIO: a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning
Doesn't seem that way, but its being discussed https://github.com/fepegar/torchio/issues/388
-
[D] Affine Transform for data boosting?
See the torchio package: https://github.com/fepegar/torchio
What are some alternatives?
segmentation_models.pytorch - Segmentation models with pretrained backbones. PyTorch.
Super-SloMo - PyTorch implementation of Super SloMo by Jiang et al.
ttach - Image Test Time Augmentation with PyTorch!
pytorch-widedeep - A flexible package for multimodal-deep-learning to combine tabular data with text and images using Wide and Deep models in Pytorch
Robo-Semantic-Segmentation - Just a simple semantic segmentation library that I developed to speed up the image segmentation pipeline
awesome-colab-notebooks - Collection of google colaboratory notebooks for fast and easy experiments
EasyOCR - Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
caer - High-performance Vision library in Python. Scale your research, not boilerplate.
3d-multi-resolution-rcnn - Official PyTorch implementaiton of the paper "3D Instance Segmentation Framework for Cerebral Microbleeds using 3D Multi-Resolution R-CNN."
mammography_metarepository - Meta-repository of screening mammography classifiers
pytorch-toolbelt - PyTorch extensions for fast R&D prototyping and Kaggle farming
Augmentor - Image augmentation library in Python for machine learning.