Skip to main content

All Questions

Filter by
Sorted by
Tagged with
0 votes
0 answers
20 views

How do I initialize a bias for the final layer of a CNN if my final output is logits and not probabilities?

I'm working on a medical image binary segmentation problem using a U-Net in tensorflow, and my classes are extremely unbalanced (about 1 in 10,000). I want to initialize a good bias for the last layer ...
Thao Nguyen's user avatar
1 vote
0 answers
752 views

How to classify unbalanced classes in image segmentation?

I'm trying to implement image segmentation for the first time, but I have trouble understanding the data format. As I understand it, my network input is supposed to be an image, so a ...
R. Hidra's user avatar
1 vote
0 answers
341 views

Neural Networks: How to set the weights for weighted sampling for semantic segmentation?

I'm currently trying to do semantic segmentation with a deep learning model on images. The dataset is highly imbalanced and i would like to try weighted sampling. I'm using pytorch and a dataloader ...
Sabse's user avatar
  • 31