how to run functions

[Palashio]

so i've got a set of 3D images (128, 128, 128) (both images and their appropriate masks). I want to run this implementation of UNet on it. How would I do this? They're .nii files so i've coded up my on dataset loader for it. I'm a bit confused on where to get started as there aren't enough reference resources.

[Palashio]

I have it working so that this is what my training script looks like so far:

    for epoch in range(epochs):
        print(' - training - ')
        for i, (images, masks) in enumerate(train_loader):
            images = images.to(device)
            masks = masks.to(device)

where images, masks are both sizes (1, 1, 128, 128, 128) and train_loader looks like this:

train_loader = DataLoader(dataset=Dataset(partition['orig'], partition['segment']), 
                          batch_size = batch_size, shuffle = True)

where partition['orig] is the original image and partition['segment'] is the segmented image. the batch size is also 1.

[zyl200846]

i will update info this weekend so that you can run the code successfully. Its been busy since i joined the job. sorry for causing inconvenience. best regards， Jielong Thanks & regards, Jielong a Hong

…

________________________________ From: Palash Shah <notifications@github.com> Sent: Friday, July 31, 2020 7:59:37 AM To: JielongZ/3D-UNet-PyTorch-Implementation <3D-UNet-PyTorch-Implementation@noreply.github.com> Cc: Subscribed <subscribed@noreply.github.com> Subject: Re: [JielongZ/3D-UNet-PyTorch-Implementation] how to run functions (#3) I have it working so that this is what my training script looks like so far: for epoch in range(epochs): print(' - training - ') for i, (images, masks) in enumerate(train_loader): images = images.to(device) masks = masks.to(device) where images, masks are both sizes (1, 1, 128, 128, 128) and train_loader looks like this: train_loader = DataLoader(dataset=Dataset(partition['orig'], partition['segment']), batch_size = batch_size, shuffle = True) where partition['orig] is the original image and partition['segment'] is the segmented image. the batch size is also 1. — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub<#3 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AHCSY2UD4D7WLGFPN2NOXT3R6ICOTANCNFSM4PO5VNJA>.

[NadiyaC249]

why i got a vary poor performance on the model ？（use the brats dataset to segment brain tumor）