Tensorflow Object Detection API - showing loss for training and validation on one graph

Question

I am playing with Tensorflow Object Detection API and training the Faster R-CNN network on my own dataset. I am checking the progress of learning at Tensorbord. All metrics are there, but is there a way to have both loss plots, for training and validation data, on one graph? Or do I have to dive into TOD Api code and modify it? I would like to avoid the second because during every update of the API I will have to keep in mind that some of the code is changed locally.

Answer 1

The underlying data for the plots is saved under different tag names (loss vs loss_1). I believe TensorBoard does not natively support displaying different tags in one plot. There might be third-party extensions to do this.

If different models used the same tag, the graphs would be combined by default (see: Plot multiple graphs in one plot using Tensorboard).