Replies: 1 comment
-
The logits can be directly used. Please refer to |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi there. I am a beginner with MMSegmentation.
I am working on a 2D binary segmentation problem; in particular, 0 = background, 1 = tumor. To post-process the result from inference, I would like to work on the softmax as it was a gray-scale image with pixel values between 0 and 1, corresponding to the probability that the specific pixel belongs to the class 1. The real issue is that I just can't figure out how to obtain it from
results
orseg_logits
.After I do this:
I think I need some function to convert logits into probabilities. But I can't find the right function to use, as whatever function I use I get the error "'PixelData' object has no attribute..." etc.
Someone told me to give this code a look but of course I'm not expert enough to figure it out on my own.
I am sure I am missing something. I would be grateful to get your help!
Beta Was this translation helpful? Give feedback.
All reactions