1
$\begingroup$

I am doing binary classification using CNN and viewing the results using tensorboard. The problem is that the tensorboard is not showing the loss and accuracy for training data.

This is the screen shit of tensorboard

As seen curves for training data are not shown

$\endgroup$
2
$\begingroup$

It is hard to know what is happening from just that screenshot and no code.

The training and validation plots are usually separated on the page, not lines on the same graph.

If you are using Tensorflow 2.0, there is a known issue, regarding the syncing of TB and the tfevent file (where logs are stored). A couple of things to try:

  1. Try adding the TensorBoard callback with the argument: profile_batch=0
  2. Try restarting the tensorboard a few times... reading can fail or be very slow to load

I am referring to the tensorflow.keras API:

tf.keras.callbacks.TensorBoard(
    log_dir='logs', update_freq='epoch',
    profile_batch=0,                      # <-- default value is 2
)
| improve this answer | |
$\endgroup$
  • $\begingroup$ Yes thank you, it was slow to load it appeared after sometime. Thank you ! $\endgroup$ – Abhinav Thapper Apr 7 at 9:20
  • $\begingroup$ You're welcome @AbhinavThapper :) please consider accepting the answer to mark the question as closed. $\endgroup$ – n1k31t4 Apr 7 at 9:34

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.