zhayanli

The results of validating a model which training with tridentnet_r101v2c4_c5_multiscale_addminival_3x_fp16.py are bad.

5

**Describe the bug** Thanks for your excellent work！ I trained my own dataset using tridentnet. I converted my dataset to coco and ran create_coco_roidb.py , then changed gpus, num_class,log_frequency to...