The training strategies

[zhuxing0]

The paper mentions that “each model was trained 90 epochs using a batch size of 64”, is this the same in the final training of Stereobase？What are the training strategies on the sceneflow and KITTI datasets respectively?

[XiandaGuo]

Thank you for your interest in our work. Since our paper has not yet been officially accepted, the code and the training strategies for Sterebase have not been released.