uk-digital-heart-project / 4dsurvival Goto Github PK

Hi,
I have noticed that in the negative likelihood loss functions there is no transpose on line 39 (https://github.com/UK-Digital-Heart-Project/4Dsurvival/blob/master/code/trainDL.py#L39). This is the code deepsurv implementation: https://github.com/jaredleekatzman/DeepSurv/blob/master/deepsurv/deep_surv.py#L165.

Hi, I have a question, I don't know why I should requires that all subjects in the input batch must be sorted in descending order of survival/censoring time. This makes me very confused. Thank you very much for answering this question for me

@lisurui6

Brief Description:

While training the 4DS network (demo_validateDL.py) using PH data from the cardiac drive, 'NaNs detected in inputs, please correct or drop' error is observed:

About the screenshot:

1. I have suppressed the N/W training progress information.
2. The training starts fine with step (1)
3. For the first bootsrap sample, the error is observed in step (2a), hyperparameter search.
   concordance.py
4. The error is 'NaNs detected in inputs, please correct or drop'

My understanding:

While finding the hyperparameters, the inputs are becoming NaNs.
Possible causes:

1. Exploding/vanishing gradient problem
2. Seeding the solver properly
3. Need of changing the inputs passed to the DL_single_run() inside hypersearch_DL()

Reproducing the error:

1. screen

2. Run the latest docker image with appropriate mounting of the volume for the following file: $PWD/cardiac/for_ghalib/backup/home/[email protected]/gbello/RWorkspace1/mesh_motiondescriptor_PHAB0267Adecmesh_CTEPH302.pkl:

nvidia-docker run -ti --rm -v $PWD/cardiac/for_ghalib/backup/home/[email protected]/gbello/RWorkspace1:/data lisurui6/4dsurvival-gpu:latest

3. cd demo

4. CUDA_VISIBLE_DEVICES='available_device' python3 demo_validateDL.py

5. Wait.

Hello, can I run it under Windows system?