Loss is not minimizing after 2nd epoch. about active-contour-loss HOT 5 OPEN

I also just reshaped my data, so that I don't have to do any other changes in the original code:

    y_true = tf.transpose(y_true2, [0, 3, 1, 2])
    y_pred = tf.transpose(y_pred2, [0, 3, 1, 2])

but unfortunately the training output is exactly the same.

from active-contour-loss.

Hello, I also encountered the same problem, have you solved it?

from active-contour-loss.

Hello!

I haven't solved the problem yet.
I contacted the author and he said that the loss is sensitive to unbalanced classes problems on diiferent datasets.

So, he suggested the following things:

1. Try to find two another well-choosed hyperparameters a and b: a* regionin + b * regionout in the region term according to your dataset.
2. Try to train with a pre-trained model (no need converged too much) to tackle the initialisation problem of model and the AC model.

Good luck!
Please update if you solve it, I wll do the same :)

from active-contour-loss.

Hi there, I solved this problem by crop my data. I think the loss is sensitive to unbalanced categories. And the learning rate is 0.0005, keep the y_pred is a probability map between [0,1]. No other code changes.

from active-contour-loss.

Thank you very much!
I can't test it for the next few weeks, but I will try and also update.

from active-contour-loss.