{{ message }}
Repository navigation
MAISI mask autoencoder #1977
Description
Hi,
Thanks for your great work with MAISI. The mask_generation_autoencoder has 8 input channels. What is the kind of data that is required as input?
Would you have an example on how to use the mask autoencoder alone, without the diffusion part based on the provided data description for mask_pseudo_label*.nii.gz ?
"mask_generation_autoencoder_def": {
"_target_": "monai.apps.generation.maisi.networks.autoencoderkl_maisi.AutoencoderKlMaisi",
"spatial_dims": "@spatial_dims",
"in_channels": 8,
"out_channels": 125,
Thanks,
Christian
Activity
Can-Zhao commentedon Aug 14, 2025
@guopengf Hi Pengfei, could you help answer this question? Thank you!
guopengf commentedon Aug 18, 2025
Hi @wachinger, you can use this function ldm_conditional_sample_one_mask to use the mask generation model alone. We will create a new tutorial on how to use a standalone mask generation diffusion model.
mar-cry commentedon Sep 9, 2025
Hi @guopengf , i am also interested in the in_channels of the mask autoencoder, what is the data type of this input ?
guopengf commentedon Sep 9, 2025
Please refer to the discussion here #2026 (comment)