dataset for pre-trained weight

[zwang573]

Thanks for your amazing work! Do we have to download and process the full nuscenes dataset if we just want use the pretrained weight for video generation?

[flymin]

You can check the demo with the webui first. They have minimal dependencies.

[zwang573]

yes we tried webui and the demo for image generation, the run.py script works pretty good but we got errors when we try to use the webui.

[zwang573]

following is the detail of the error message:

ERROR: Exception in ASGI application Traceback (most recent call last): File "/home/user/persistent/miniconda3/envs/magicdrive/lib/python3.8/site-packages/pydantic/type_adapter.py", line 270, in _init_core_attrs self._core_schema = _getattr_no_parents(self._type, 'pydantic_core_schema') File "/home/user/persistent/miniconda3/envs/magicdrive/lib/python3.8/site-packages/pydantic/type_adapter.py", line 112, in _getattr_no_parents raise AttributeError(attribute) AttributeError: pydantic_core_schema

During handling of the above exception, another exception occurred:

File "/home/user/persistent/miniconda3/envs/magicdrive/lib/python3.8/site-packages/pydantic/_internal/_generate_schema.py", line 558, in _unknown_type_schema raise PydanticSchemaGenerationError( pydantic.errors.PydanticSchemaGenerationError: Unable to generate pydantic-core schema for <class 'starlette.requests.Request'>. Set arbitrary_types_allowed=True in the model_config to ignore this error or implement __get_pydantic_core_schema__ on your type to fully support it.

If you got this error by calling handler() within __get_pydantic_core_schema__ then you likely need to call handler.generate_schema(<some type>) since we do not call __get_pydantic_core_schema__ on <some type> otherwise to avoid infinite recursion.`

[flymin]

https://github.com/oobabooga/text-generation-webui/issues/6367 is this related?

[github-actions[bot]]

This issue is stale because it has been open for 7 days with no activity. If you do not have any follow-ups, the issue will be closed soon.