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
.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.