Closed fabioperez closed 7 years ago
Hi Fabio,
I think what you're missing is the arguments to the CRF3DProcessor. Please take a look at https://github.com/mohamed-ezz/saratan/blob/master/validation/pipeline/miccai_pipeline/predictor.py#L161
There you can find the params passed to CRF3DProcessor object as well as any processing for the inputs of set_data_and_run(...)
@mohamed-ezz Thank you! The prediction.py
code helped a lot!
Hello,
I'm trying to reproduce your results and I'm having trouble with the CRF step. Following the ipython notebook, I'm using image 17 from 3DIRCAdb1. I've made some modifications in the notebook to run the network for every slice. Without CRF, I got a dice score of 0.8573.
I cloned and installed https://github.com/mbickel/DenseInferenceWrapper/. However, I'm not sure how I can use it. I'm trying the following:
Where
img_preprocessed
is the preprocessed image without the padding reflections (dimensions(W,H,D)
; andextended_labels
is the output of the predictions (direct probabilities, not thresholded bool) with dimensions(W,H,D,L)
(where L = 1). I'm getting a(W,H,D)
matrix with zeroes.Can you help me with this?