Closed bhack closed 7 years ago
It didn't work because there is some numeric instability in the training with the logarithmic function. You can find more information in the TensorFlow inplementation without the class balancing.
Ok this passages remove also sigmoid(). Why you have used:
labels = tf.cast(tf.greater(label, 0.5), tf.float32)
I used this to make sure that the labels are binary with 0 or 1 values.
Yes I understand this but Davis png annotation are not already 0 or 255?
Yes, DAVIS has these values, but not all databases do. So I wrote this to enforce that the value of the labels is always correct.
Thanks
Hi, I have a question.
Why the line 800 in the osvos.py use 162.0/255.0 instead of 0.5?
res_np = res.astype(np.float32)[0, :, :, 0] > 162.0/255.0
We use this threshold instead of 0.5 because it's the optimum. However, the results using 0.5 are almost the same.
Thanks!
Do you have any more info why class_balanced_cross_entropy_loss_theoretical didn't work so well?