search

lucasmansilla / ACRN_Chest_X-ray_IA

Learning Deformable Registration of Medical Images with Anatomical Constraints
MIT License
23 stars 9 forks source link

index 50 is out of bounds for axis 0 with size 50 #16

Open tracob-github opened 2 years ago

tracob-github commented 2 years ago

Thanks for sharing this excellent code.

When I run test_aenet.py, an error occurred. image After debugging, I found that the size of test_lbs and z in models.py are inconsistent. The size of test_lbs is (50, 256, 256, 1), but the size of z is (800, 64, 64, 1). As show in two pictures. 1632383057 1632383057(1)

I would like to ask how to sovle it.

lucasmansilla commented 2 years ago

Hi @tracob-github,

AE-Net runs with 64x64 segmentations. What size of segmentations are you using?

tracob-github commented 2 years ago

Thank you!I know where the problem is. I try to reproduce your work, and the accuracy of test_aenet is about 0.97. Is it correct？

Westbrone commented 1 year ago

Hello, your code is written very well, but because there is no pre-training model of the autoencoder, when I was training the model, the loss remained at around 0.49 in the end. Is it because of the pre-training model?