Thanks to visit codestin.com
Credit goes to github.com

Skip to content

The test result of COCO by using faster-rcnn #27

@TIEHua

Description

@TIEHua

Sorry to bother you. I use faster-rcnn to test COCO. The mAP is 12.7%, which is lower than the result in the paper (15.7%);
The parameters I used are the default parameters in the trainval_net.py. How many epochs do you choose for training? Thanks for your time. I am waiting for your reply.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions