This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

TDA2EVM5777: Caffe jacinto: question of a hyper parameter

Part Number: TDA2EVM5777

Hello,

In the train_image_object_detection.sh for SSD training, there's a parameter called min_dim which was noted as impacting the accuracy of trained networks much.  

What does the min_dim parameter actually control in SSD?

Thanks,

Wei Chih