About Stage 1: Data pre-processing and computing features

[JWZhao-uestc]

Thanks for your awesome work. I want to confirm implementations about data pre-processing.

I think, I should replace the Resnet18 with CtransPath to train the embedder using SimCLR. And load the pre-trained CtransPath model before training embedder. After that, I should use the trained embedder as feature extractor.

Could you please tell me if my implementation is correct? If not, could you please tell me what I should do correctly.

Thank you!

[HHHedo]

If you want to train CtransPath using SimCLR, you can just leave it randomly initialized. If you want to use the pre-trained CtransPath, you do not need to train the embedder but directly use it.

[JWZhao-uestc]

Thanks for your reply. I will try it again.