How could I construct a neck structure similar to unet by the output of some feature extraction layer (conv2D)

[zzc-ai]

How could I construct a neck structure similar to unet by the output of some feature extraction layer (conv2D) my code :from efficientnet_pytorch import EfficientNet model = EfficientNet.from_name('efficientnet-b0') list(model.children())[2]

I found that all the extracts had been integrated under a large framework. How to extract them and put them into structures such as UNET and FPN

[lukemelas]

Check out https://github.com/zhoudaxia233/EfficientUnet-PyTorch, which is built on this repo

[zzc-ai]

thank you ,i will try and learn it ,i have saw that ,it will helpful ,