Multiple runs on training not evaluation about siamese-mask-rcnn

[michaelisc]

Hi @MSiam we did not explicitly test this. In my experience the differences are small but I did never try to quantify this. In general the stochasticity during training is smooted by the fact, that we train for 160k steps with random references at each step. The remaining component is the randomness of the initialization, which is the same for all networks and has small effects for standard Mask R-CNN models.

[MSiam]

Thanks for your reply