Zhao (Dylan) Wang
Zhao (Dylan) Wang
Any update?
Maybe you can refer to my repo: https://github.com/Kyfafyd/MirrorGAN Hope helpful to you!
How your face dataset is formulated?
Can you show me some more details of your current status? e.g. the dataset url. code .etc Sorry for replying so late, I am on several urgent projects...
I have tried to apply MirrorGAN to a medical image generation task. So this is specified for that task, you can generate for your own by modifying this.
That is just a reference, I think this part is not difficult, you can further try it on your own.
Hi, @Dorothy-h357h Thanks for your interest in our work! Unfortunately, these weights have been deleted before due to storage issue. You can directly train these models on our dataset with...
We use the ST-Adapter in ViT and just finetune ST-Adapter during pre-training, i.e., the other parts are fixed.
You may refer to this file of ST-Adapter: https://github.com/linziyi96/st-adapter/blob/main/models_adapter.py Only the adapters in ViT are trained, just like: https://github.com/linziyi96/st-adapter/blob/b914b388f45ddd1968348ae2b1590a17eca75f8f/models_adapter.py#L196-L199 And video forwarding is like: https://github.com/linziyi96/st-adapter/blob/b914b388f45ddd1968348ae2b1590a17eca75f8f/models_adapter.py#L207-L230
Hi, thanks for your interest! The normailzation is using the ImageNet values: https://github.com/med-air/Endo-FM/blob/c0979d2d235a61f85daf171a73a34f47683a67d9/datasets/transform.py#L679-L681