Closed bodokaiser closed 7 years ago
I just noticed that our ElasticNet implementation is numerically unstable (result yields nan's).
I found the problem with why data varnishes after one epoch. The reason is that MNIBITENative
calls to Normalize()
overwrite the images such that with a second normalize (over the original value range) it has lost its precision. I try to find a way that MINC2
loads the corresponding image slice directly over h5py.File
each time.
Rebased with master.
1. Precision
To increase image precision on MRI images we would need to:
MINC2
asnp.float64
network
models to use weights, etc. asLongTensor
sscripts/patch.py
to save images as TIFFsMNIBITEFolder
to load TIFF patches2. Filtering
To support our enhanced loss function we need to create a binary mask from US thresholding. That mask can also be used to filter too small US images (saves us one calculation) in the training loop.
3. Enhanced Loss
support batchesBugs