What am I supposed to see on tensorboard images tab?

I'm training an object detection model with Tensorflow and monitor the training task with tensorboard. I was expecting in the Images tab of tensorboard that displayed images would show a bounding box (at a specific point of training). What I see though is only images with an orange line drawn above the picture (the same orange that I expect for the bounding box). Am I missing something? Am I right when I say that a bounding box should appear or not? Picture of what I see is joined. Any help greatly appreciated.

Topic object-detection training tensorflow evaluation

Category Data Science

1
answered at

This is what I see using data from Pascal VOC that was converted using this example script: Images from Tensorboard

I am using Tensorflow 2. I think it's just the images preprocessed using the data_augmentation_options that were specified in your pipeline.config file.

I seem to recall seeing bounding boxes on the images in Tensorboard back when I was using the Object Detection API with Tensorflow 1. But I haven't seen any bounding boxes on the images using the API with Tensorflow 2. I have verified that the models subsequently worked. I just didn't see bounding boxes in Tensorboard. Note that I am just running training and then doing evaluation separately. If you specified eval_config or eval_input_reader in your pipeline.config, you might get different results.

About

Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.