Why not using `.fit()` method to train TF2 model?

Hey all!
I am following your example here in my own codebase to train a GCN. My question is, since GCN is a child of tf.keras.Model, why can’t we use .compile() and .fit() to do training? Does it relate to the performance drop mentioned here? Thanks

I tried calling .fit() instead of using tf.GradientTape() and I got this error related to DGLDataset object. Any help? Thanks

DGL has some customized operator which cannot be scripted by Tensorflow. Thus only eager mode is supported for now

I might be missing something, but isn’t .fit() eager mode?

This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.