Matthew Ward
Matthew Ward
Thanks @wasserth. Could I ask why the weights are being redownloaded on each script execution? I'm no expert on the nnU-Net algorithm but I would have assumed that this information...
Okay thanks so I suppose this must be some issue with my installation then, that it wasn't able to download the weights then so it is reattempting the download on...
Will this work if I want to keep the structure names the same but enhance two particular small volume contours (the cochleae)? e.g. }, "labels": { "background": 0, "Brain": 1,...
> For the second issue if it is not solved yet: > > We encountered exactly the same problem today, on a system of 96GB RAM. It turns out to...
Can anyone assist with this please?
Thanks @FWijanto. No I have only been using the standard planner thus far. With only 16Gb of VRAM currently available we are unable to run the recommended ResEnc L planner....
Thanks @FWijanto, I gave the ResEncM planner a shot and after 80 epochs the average epoch time was nearly 4 hours, meaning it would take a year and a half...
I'm not sure if this is completely relevant, but I managed to avoid a similar dead worker error by taking lines 38-40 in nnunetv2/training/dataloading/utils.py np.load(data_npy, mmap_mode='r') if isfile(seg_npy): np.load(seg_npy, mmap_mode...