Data Input for Instance Segmentation

Instance segmentation expects directories of images for training or validation and annotation files in COCO format. See the Data Annotation Format page for more information about the data format for image classification.

The naming convention for train/val split can be different because the path of each set is individually specified in the data preparation script in the IPython notebook example. Image data and the corresponding annotation file is then converted to TFRecords for training.

© Copyright 2020, NVIDIA. Last updated on Aug 24, 2021.