search

BioMedAI-UCSC / InverseSR

[Early Accepted at MICCAI 2023] Pytorch Code of "InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion Model"
http://arxiv.org/abs/2308.12465
Apache License 2.0
50 stars 7 forks source link

Pretrained models #13

Closed otsab19 closed 2 months ago

otsab19 commented 2 months ago

@jueqiw What are the pre trained vae and vgg16 models being used here? There are no files in the drive. Is the files somewhere or its being trained by yourself?

otsab19 commented 2 months ago

nvm found it

Willow-WYL commented 4 weeks ago

@otsab19 Hi! I have encountered the same question! Where did you find vae?

otsab19 commented 4 weeks ago

https://github.com/BioMedAI-UCSC/InverseSR/issues/9

Willow-WYL commented 4 weeks ago

@otsab19 I found vgg in that, what about vae? Thank you so much!!!

jueqiw commented 4 weeks ago

@Willow-WYL Can you point out where in the code use the vae? Thanks!

Willow-WYL commented 2 weeks ago

@jueqiw sorry! i didnt see your reply last week! when i tried to test the model DDIM, I run the InverseSR_DDIM.sh, got the error as follows: FileNotFoundError: [Errno 2] No such file or directory: '/InverseSR-main/data/trained_models/vae/data/model.pth'

Willow-WYL commented 2 weeks ago

@jueqiw i believe it means that there should be a pretrained vae model?

jueqiw commented 2 weeks ago

@Willow-WYL Can you tell me which line and file caused that error?

Willow-WYL commented 2 weeks ago

@jueqiw utils.py line121