search

ge-xing / Diff-UNet

Diff-UNet: A Diffusion Embedded Network for Volumetric Segmentation. (using diffusion for 3D medical image segmentation)
Apache License 2.0
141 stars 20 forks source link

BTCV/test.py label input. #16

Open ToruHironaka opened 1 year ago

ToruHironaka commented 1 year ago

Program file "BTCV/text.py " a line of code at the line number 100 below. This line of code should be batch["label"] instead of batch["raw_label"]. Because batch["raw_label"] does not match with input's volume sizes.

label = batch["raw_label"] --> label = batch["label"]

image

920232796 commented 1 year ago

You should use the "raw_label" in the test phase.

image

We should compute the metric using the "out" and "label" with original size.