Mask_rcnn: How can I compute the AP of my own datasets

Created on 13 Aug 2018  路  1Comment  路  Source: matterport/Mask_RCNN

When I finished training my own dataset, I can't do anything to compute the accuracy as well as the AP of my running.How can I work it out?
Thanks for your attention.

Most helpful comment

Check train_shapes.ipynb
functions in utils.py including compute_ap will help.

>All comments

Check train_shapes.ipynb
functions in utils.py including compute_ap will help.

Was this page helpful?
0 / 5 - 0 ratings

Related issues

AshleyRoth picture AshleyRoth  路  37Comments

luoshanwei picture luoshanwei  路  167Comments

rujiao picture rujiao  路  82Comments

hxw111 picture hxw111  路  39Comments

lokinfey picture lokinfey  路  32Comments