-
Create a function to perform a one-subject segmentation.
The function would have the following inputs: (i) path to image, (ii) path to save the segmentation, (iii) path to trained model. This funct…
-
### Description
Just by executing `sct_utils` got the following error message instead of getting the usual help message:
```
Traceback (most recent call last):
File "/home/shernand/sct_4.3/sc…
-
When running the following command, an error is raised:
~~~
julien-macbook:~ $ sct_check_dependencies
Traceback (most recent call last):
File "/Users/julien/code/sct/scripts/sct_check_dependenc…
-
The code in tumor_segmentation/main.py (https://github.com/neuropoly/ivado-medical-imaging/blob/al/tumor_segmentation_UNet2D/tumor_segmentation/main.py) is essentially the same as ivadomed/main.py (ht…
-
The base U-Net currently takes ~600 seconds per epoch to train, while FiLMed U-Net takes ~340s. This makes no sense since FiLM adds complexity to the model, thus it should take longer to train (which …
-
See comment: [comment](https://github.com/neuropoly/ivado-medical-imaging/pull/28#issuecomment-505562057)
We also need to add `matplotlib` as requirement, see [comment](https://github.com/neuropoly…