Deep learning model for the classification of poses in images using Mask RCNN and VGG19. This model classifies 15 different poses. Model can be easily adapted to classify new poses (maximum of 2 persons) provided that the dataset is given. Outline of model architecture is here. Archive of submission for Today I Learned Ai Camp 2019, with a final validation score of 0.70989.
Clone this github respository
!git clone github.com/CannyAss/Pose-Detector
A step by step series of examples that tell you how to get a development env running
Say what the step will be
Give the example
And repeat
until finished
End with an example of getting some data out of the system or using it for a little demo
Explain how to run the automated tests for this system
Explain what these tests test and why
Give an example
Explain what these tests test and why
Give an example
- Mask_RCNN - The library used for instance segmentation
- Keras - The deep learning module used for classification
- Chengyang - Generation of good masks from dataset
- Warren - Selection and curation of deep learning model
- Wei Kiat - A little bit of both
- Yuqing - Visualisation of pipeline and presentation
- Defence Science and Technology Agency for the dataset and competition experience