Yuxin Du

Thank you very much! I'll try it again with new hyper-para.

I still got some problem in training using the new super-para. Part of tensorboard info:   The min value point in total loss figure is about 20000 steps,...

Thanks for your detailed reply! I just tried the new division of dataset and got a better score: 76.01(AP50).  But you know, it's still lower than the score presented...

Add a little bit of my understanding: assuming a manually set ratio, the trainer can adjust the hyperparameter using the result of eval. Your work just automates the process. Is...