Describe the bug
Thanks for your excellent work！
I want to train my own dataset using tridentnet. I convert my dataset to coco and run create_coco_roidb.py , change gpus and num_class in config. Do I need to change another parameters?
Screenshots or stack traces
If applicable, add screenshots or stack traces to help explain your problem.
Which config are you using
Which dataset are you using
Hardware info
CPU, GPU, Storage(Disk or NFS)
Software info
driver, CUDA, cuDNN versions
OS verison
How did you set up your MXNet for SimpleDet
Additional context
Add any other context about the problem here.
Describe the bug Thanks for your excellent work！ I want to train my own dataset using tridentnet. I convert my dataset to coco and run create_coco_roidb.py , change gpus and num_class in config. Do I need to change another parameters?
Screenshots or stack traces If applicable, add screenshots or stack traces to help explain your problem.
Which config are you using
Which dataset are you using
Hardware info CPU, GPU, Storage(Disk or NFS)
Software info driver, CUDA, cuDNN versions OS verison
How did you set up your MXNet for SimpleDet
Additional context Add any other context about the problem here.