Track your Instance Segmentation model predictions with DeepSortMask. This repository explains how to use deep_sort to track masked objects from MaskRCNN.
8
stars
1
forks
source link
Hi, I want to train my own dataset for goal tracking in this project, how should I do it? #1
Hi, sorry for late reply but if you are still interested in the answer here you go
you will have to train a segmentation model for goal segmentation in tensorlow and then you can use this to track the segmentation outputs of each frame. refer to this for training: https://towardsdatascience.com/mask-rcnn-implementation-on-a-custom-dataset-fd9a878123d4
I would love to answer in detail if required.