Haoyang Fang

@zhiqiangdon Shall we initialize `self._config` in `learner.__init__` to avoid using `self._hyperparameters`?

TODO: 1. Add num_to_keep for HPO in our multimodal configs instead of hardcoding it: https://github.com/autogluon/autogluon/blob/c51aa59cd4c32fd96420c79140fd832e7dd09fc7/multimodal/src/autogluon/multimodal/utils/hpo.py#L175 2. Add checkpoint selection (and cleaning) before HPO to reduce the peak storage: https://github.com/autogluon/autogluon/blob/c51aa59cd4c32fd96420c79140fd832e7dd09fc7/multimodal/src/autogluon/multimodal/learners/base.py#L597

Add installation instruction (downgrade torch to 2.1.0) in https://github.com/autogluon/autogluon/pull/4447.

Fixed in [#4430](https://github.com/autogluon/autogluon/pull/4430). pynvml is not listed as it's no more needed as dependency.

It might be that the model is not robust enough, and there are outputs Nan value in prediction head. We have changed the default preset to use YOLOX-large instead of...

I'm unable to reproduce the reported bug. When simulating the issue by inserting an `exit()` line at the checkpoint fusing stage, the current code functions correctly. However, the pull request...

Hi @allandclive, could you provide the complete error message?

For google Colab this works: ``` !pip install autogluon.multimodal !pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 !pip install "mmcv==2.1.0" -f https://download.openmmlab.com/mmcv/dist/cu121/torch2.1.0/index.html !pip install "mmdet==3.2.0" ```

Update the tutorial in https://github.com/autogluon/autogluon/pull/4447. Closing the issue. Feel free to reopen it if the problem still exists.

Fix the issue in: https://github.com/autogluon/autogluon/issues/4421