Jun

So weird. I do not have experience with deepmedic, but I try U-Net with brats2018, it works well. Do you have similar problem with U-Net in niftynet.

@sara-eb Following is my personal understanding of the parameters. @taigw Please correct me if I’m wrong. Thank you for the awesome repository. ```python dense_crf_param = {} dense_crf_param['MaxIterations'] = 2.0 #...

Dear @jeanfeydy , Thanks for the excellent work. > OT theory is always concerned with measures, distributions of mass. > Consequently, ImagesLoss and VolumesLoss will be best suited to the...

Moreover, it seems Wasserstein distance has computational problems. how big an image can be calculated by ImagesLoss and VolumesLoss in practice? (In general, the size of 3D medical CT images...

Hi @jeanfeydy , Thanks for your quick and detailed reply very much. I'm confused when comparing the above `to_pointcloud` function and `RGB_cloud` function in the [color transfer](http://www.kernel-operations.io/geomloss/_auto_examples/optimal_transport/plot_optimal_transport_color.html) demo. ```python def...

Dear @jeanfeydy, Thanks for sharing the great work. I hope everything goes well with your PhD thesis. > Anyway, in two or three months, all of this (+ all the...

Hi, @life-8079 We only use the tumor cases. The remaining cases do not have tumor:)

Please make sure your monai version is 0.9.

If you are using the old MONAI, please try to remove the data augmentation https://github.com/JunMa11/NeurIPS-CellSeg/blob/2df1ee5dc26b4ff10202da73ef22d72651e8e5bd/baseline/model_training_3class.py#L128-L148

We cannot reproduce your error. - please delete the data and re-run the preprocessing. - Have you tried to remove the data augmentation?