Shahbaz Khan
Results
2
comments of
Shahbaz Khan
@hsinyilin19 I am afraid that's not correct. The default code (pretrained=True) simply loads the pretrained weights but doesn't freeze them. I have opened a [PR](https://github.com/hsinyilin19/ResNetVAE/pull/4) to freeze them.
I encountered the same issue. The `ChatGoogleGenerativeAI` class throws this error with Pydantic schema. What worked for me is the following: Instead of doing `(prompt | llm.with_structured_output(Schema)).invoke({})`, instead do `chain...