Carlo Russo
Carlo Russo
I confirm that the model works fine. To get high dice scores you will need to train the model for at least 100-200 epochs, depending on the dataset. I used...
This model requires huge GPU power. The author used a V100 equipped with 32 GBytes of Graphic Memory and used a crop size of 160x192x128. In my training I cropped...
You should not have a "nan" as a loss value. Maybe there is something wrong in your loss function, try double checking it.
In my experiments I trained the model using the loss function as the sum of L=-dice+0.1*KL+0.1*L2. I wonder if you used only the VAE part of the terms instead of...
To help discover the reason of the Nan values, I suggest to check separately the terms of the loss function. You can add more metrics and check which one is...
Duplicate of #122
Dear @li6364 I just tried to install lisflood in a new conda environment following the installation steps in the guide and it is working. To help you on this issue...
Unfortunately we do not provide support for Windows OS. Can you please send the Linux version and related logs?
The full installation should be done on a Linux operating system. Thus you need to create the conda env in a Linux OS.
@corentincarton I actually use it to check the unit tests every time I push something new on any branch, instead of waiting for them to be merged in develop. However...