Closed mpompolas closed 11 months ago
"training_validation": [
"T1w",
"T2w",
"T2star"
],
I'm pretty sure that sct_testing-large
include other suffixes.
"fname_split": "/home/GRAMES.POLYMTL.CA/u111358/data_nvme_u111358/ivado-project/Datasets/split_datasets_converted.joblib",
"early_stopping_patience": 50,
Reminder for later: we will need to modify the postprocessing
and evaluation_parameters
Increase Affine DA, eg degrees
to 20
and translate
to 0.1
"RandomAffine": {
"degrees": 5,
"scale": [
0.1,
0.1
],
"translate": [
0.03,
0.03
],
"applied_to": [
"im",
"gt"
],
"dataset_type": [
"training"
]
},
CropSize
params and the strenght of the ElasticTransform
.Reminder for later: we will need to modify the postprocessing and evaluation_parameters
Hey @charleygros, I am training SoftSeg models using @mpompolas's config + your suggestions. I was wondering what else needs to be changed in the config for postprocessing and evaluation params. Thanks!
Hey @charleygros, I am training SoftSeg models using @mpompolas's config + your suggestions. I was wondering what else needs to be changed in the config for postprocessing and evaluation params. Thanks!
Oh yea so, here my suggestion for these two chunks:
"postprocessing": {},
"evaluation_parameters": {},
yea :-) For the SC segmentation task, the remove noise, the target size etc is not so relevant. I think at this stage we don't want to add fancy postprocessing steps. Especially: no thresholding!
closing as we're not using config files or ivadomed
Training will take place on
sct-testing-large
andUK-biobank
.Config file:
For the training part we will have CenterCrop.
For the testing, we will change to ROICrop with
centerline
.Any comments @charleygros ?