The goal of this project was to create multi-modal implementation of Transformer architecture in Swift for Tensorflow.
Also it was an attempt to answer the question if Swift for Tensorflow is ready for non-trivial work.
The use-case is based on a paper "Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks" by Matthias Plappert. He created a nice dataset of few thousand motions "The KIT Motion-Language Dataset (paper)", website.
The Motion2Language and Lang2motion Transformer-based models were implemented. Also some more sophisticated motion generation strategies were tried.
Modified Swift Transformer implementation by Andre Carrera was used.
original: 2017-06-22.zip
processed:
annotations and labels:
vocabulary
link |
Stars: 7 |
Last commit: 2 years ago |
Scaled motions, using simplified MotionSample, and actual motion recording frequency when downsampling.
Swiftpack is being maintained by Petr Pavlik | @ptrpavlik | @swiftpackco | API | Analytics