search

Project-MONAI / GenerativeModels

MONAI Generative Models makes it easy to train, evaluate, and deploy generative models and related applications
Apache License 2.0
555 stars 78 forks source link

475 add different downsampling methods to patch gan discriminator #479

Closed StijnvWijn closed 3 months ago

StijnvWijn commented 3 months ago

Added features according to issue #475 leaving the default behaviour the same. According to my testing it should be as fast as the previous implementation.

Additionally, I fixed the 2D_spade_VAE.py tutorial, as it didn't work on my Windows laptop.

virginiafdez commented 3 months ago

@StijnvWijn thanks for fixing the tutorial. Since the tutorial file has undergone a lot of changes, could you create a different issue and PR for this? It's a different issue from the one treated in this one, so we would like to treat them separately. Just copy-pasting the tutorial of this branch into the new PR would suffice. Thanks.

virginiafdez commented 3 months ago

In addition, could you add use cases to test _test_patchgan.py that uses the available pooling methods? No additional test is needed, just additional configurations in TEST_3D and TEST_2D.

virginiafdez commented 3 months ago

Things work, I ran the autofix script and committed these changes.