Junwei Deng

You may initialize another Trainer ```python # ... autoformer.fit(train_loader, epochs=2, batch_size=32) trainer = Trainer(...) trainer.fit(autoformer.internal, train_loader) ``` #### reproduce result Not only Autoformer, if you carry out the same process...

@shane-huang @liangs6212 please have a look and provide some feedback if possible.

> Another related topic we may consider. Shall we separate chornos further into chronos-forecaster, chronos-detector, and chronos-simulator, chronos-data? This might make Chronos too complex, and since detector and simulator are...

pls rebase and we just need to make sure the github actions can be passed

maybe we can add ut for this pr in https://github.com/intel-analytics/BigDL/blob/main/python/nano/test/onnx/pytorch/test_onnx.py

We can follow such overview for this page, currently this draft is kind of like an API doc :) Maybe use a jupyter notebook and transform to html could be...

Will hold this PR until #5175 is merged

If you are in a new session, then you should define a forecaster first, then load it **ny** -> **by** filename. others LGTM

only `jit_fp32_ipex` seems to be a problem, will have a look

I think we could provide a "warmed-up" model to our users once uses call `InferenceOptimizer.trace` with accelerator="jit". We do this in `InferenceOptimizer.optimize` while not in `InferenceOptimizer.trace`.