-
here, it woudl be better to just define a variable wiht absolyte path, so that if you change folder, the variable will still work
https://github.com/ivadomed/model_seg_sci/blob/f2df15c659cf47908e2d…
-
### Context
Historically, SCT has used `Keras`/`tensorflow` for its deep learning-based segmentation methods (`sct_deepseg_sc`, `sct_deepseg_gm`, `sct_deepseg_lesion`). However, #2639 introduced th…
-
### Motivation for the feature
My config file does NOT include any wandb field, yet training with ivadomed used wandb:
~~~
2023-01-01 18:25:54.402 | INFO | ivadomed.loader.loader:load_dat…
-
**Describe the bug**
Importing `AxonDeepSeg/segment.py` on its own creates OpenMP an error.
This does not happen when using the CLI functions that ADS provides.
It also does not happen when using …
-
After introducing #2639, models need to be created with appropriate json metadata, notably the field `threshold` needs to be adjusted for each model.
-
See [this tutorial](https://github.com/Project-MONAI/tutorials/blob/main/modules/2d_slices_from_3d_training.ipynb), notably the 'squeeze dim', which I am currently [not doing](https://github.com/ivado…
-
here's suggestion-- please replace with proper variables:
```console
# get centerline
# if it doesn't work, do it manually
sct_get_centerline -i sub-zh48_ses-01_acq-sag_T2w_resample.nii.gz -meth…
-
> **Note**: This issue used to cover the tasks of supporting both Python 3.8 and Python 3.9. However, Python 3.8 support was added in https://github.com/spinalcordtoolbox/spinalcordtoolbox/pull/3916, …
-
Some denoising filters are quite powerful, and could potentially help during model training/testing. Eg:
```bash
sct_maths -i sub-P001_UNIT1.nii.gz -denoise 1 -o sub-P001_UNIT1_denoised.nii.gz
`…
-
## Issue description
I'm training a 'softseg' network and got this error:
Terminal output
```console
[32m2022-12-20 11:20:54.181[39m | [1mINFO [22m | [36mivadomed.training[39m:[3…