Set device = -1 but still using GPU

[A-baoYang]

Hi @emfomy , thank you for your attention 🙏

ckip_transformers version

0.2.7

What happened

Set device = -1, but the model still uses GPU.

script:

from ckip_transformers.nlp import CkipNerChunker
ner_driver = CkipNerChunker(level=3, device=-1)
res = ner_driver(text_list)

Before running the script:

After running the script:

What do you think should happen instead

It should not consume GPU resources.

How to reproduce

Run the script in GPU enable env:

from ckip_transformers.nlp import CkipNerChunker
ner_driver = CkipNerChunker(level=3, device=-1)
res = ner_driver(text_list)

Operating System

Ubuntu 20.04.2 LTS

Development Environment

• Python 3.8.12
• PyTorch 1.9.0+cu111
• Transformers 4.7.0
• Tensorflow 2.11.0

Anything else

I've checked the source code, self.device is set as "cpu", and both model and data tensor has to(self.device), so it's weird to have this problem.
And if the environment has no GPU, the model script is still runnable.

[emfomy]

It seems to be a bug related to PyTorch's DataLoader with the pin_memory option enabled. The tensor in dataloader is always pinned on GPU.

To avoid this bug, please use pin_memory=False while calling the driver (see here).

I might set pin_memory defaults to False in the future version.

[emfomy]

Fixed in v0.3.3.

[A-baoYang]

Thank you so much for the updates!