Published March 5, 2020 | Version 1.0

pedropro/TACO: Mask-RCNN weights trained on TACO-10

Authors/Creators

  • 1. NASA-JPL

Description

These weights were obtained for 4-fold cross validation using TACO-10 class map. Each file with the name: <dataset>_<map_number_of_target_classes>_<fold number>.zip contains the following:

  • The actual weights: mask_rcnn_taco_<epoch number>.h5. Copy this to detector/models/logs
  • The respective dataset split used: annotations_0_<subset>.json. Copy these 3 files to your dataset directory.

More details coming soon

Files

pedropro/TACO-1.0.zip

Files (24.4 MB)

Name Size Download all
md5:ea939251625b80da8555126b474783fa
24.4 MB Preview Download

Additional details

Related works