With the announcement that Object Detection API is now compatible with Tensorflow 2, I tried to test the new models published in the TF2 model zoo, and train them with my custom data. However, I have ...
Abstract: In this paper, we propose a novel network framework for indoor 3D object detection to handle variable input frame numbers in practical scenarios. Existing methods only consider fixed frames ...
Abstract: We propose an effective combination of discriminative and generative tracking approaches in order to take the benefits from both. Our algorithm exploits the discriminative properties of ...
Update: This README and Repository is now fully updated for Tensorflow 2. If you want to use Tensorflow 1 instead check out my article. If you want to train your model in Google Colab check out the ...