Testing of the model #41
Comments
|
Did you train your model to predict multiple classes? |
|
Yes we did the training with the exact same code you last committed. Also changed config file n_labels=4 |
ellisdg
added a commit
that referenced
this issue
Nov 18, 2017
1) Uses SimpleITK if N4BiasFieldCorrection cannot be found by nipype (closes #52 & closes #32). 2) Adds predict.py file that uses the trained model and writes the predicted labels to file (closes #51). The predictions are now multi-label (closes #41 & closes #36). 3) Fixes relative import (closes #49). 4) Removes "pickable" flag from training which fixes and closes #47. 5) Adds batch normalization option (closes #39). 6) Adds option to use patch training. This is will substantially reduce the memory requirement for training. 7) Updates README. Links to data that do not require registration (closes #37).
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hello @ellisdg Can you provide some inputs on how to view prediction.nii.gz that is generated after testing. Also please explain what is multi-class classification is doing exactly? I guess it is producing the label map but when I see the image in ITK Snap I can see only red aand green patches in the image. Any help in this regard is greatly appreciated.
The text was updated successfully, but these errors were encountered: