-
Notifications
You must be signed in to change notification settings - Fork 1
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Replicating DSRGAN.ipynb and using other planes (Trans-ventricular, Trans-thalamic, and Trans-cerebellum) #40
Comments
When calculating the FID, do I need to calculate the FID for the GAN network or for the diffusion model, or do I need both? |
FID score is computed with the following lines from this notebook: https://github.com/budai4medtech/xfetus/blob/main/examples/difussion-super-resolution-gan/DSRGAN.ipynb (also available in google colabs https://colab.research.google.com/drive/1Cbudr2g5qdC2LGBj_xYS-amgJQ-6OVM6?usp=sharing). I would suggest to running all the notebook in your google colabs and then read It would be great if you get FID for both GAN and diffusion model. Let me know how it goes. Thanks, --Miguel
|
When I run the notebook, only one value appears for FID, and only three FID values appear after running three labels. In this case, how can I draw FID value to achieve that image? It is appreciated for answering my question in your busy time. --Qingyu Yang |
Hi Qingyu, you need to read |
Qingyu Yang reported the following error
Also I noted that notebook is not updated
!pip install -qqq medisynth
https://github.com/budai4medtech/xfetus/blob/main/examples/difussion-super-resolution-gan/DSRGAN.ipynbThe text was updated successfully, but these errors were encountered: