So, I created a TensoBoard callback, but, I'm training for 1000's of epochs, and when I view TensorBoard, it is too sluggish because of the enormity of the data to be loaded and plotted, basically millions of datapoints, that's because it is writing everything happening at a batch level. I want only results at the end of epoch, not batch. Can I get to control that? Additionally, it is by default recording: loss, validation loss, and plenty other things that I didn't ask for. How can I control what is being recorded?
Try update_freq=10000.
This will make it update every 10000 sample.
Or maybe update_freq='epoch', this will update after the epoch end.
https://github.com/keras-team/keras/blob/master/keras/callbacks.py#L997