We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
请将下面信息填写完整,便于我们快速解决问题,谢谢!
问题描述 请在此处详细的描述报错信息 我在GPU环境去运行PaddleNLP的taskflow,其中使用了UIE-X-Base模型,在taskflow中,我希望用fp16精度去提高预测速度 代码如下: ie = Taskflow('information_extraction', schema=schema_obj, batch_size=batch_size, model=‘uie-x-base’, layout_analysis=True,precision='fp16') 在GPU环境安装了必要的依赖:onnxruntime-gpu onnx onnxconverter-common paddle2onnx 这是我试过的依赖的版本 onnx 1.17.0 onnxconverter-common 1.14.0 onnxruntime-gpu 1.14.1 paddle2onnx 1.3.1 paddlenlp 2.8.1 /2.7.0 paddleocr 2.9.1/2.7.0.0 paddlepaddle-gpu 3.0.0b2/2.6.2 但是初始化Taskflow的时候总是抛出module 'paddle2onnx' has no attribute 'command' 麻烦给个建议 怎么解决,多谢
更多信息 :
报错截图
其他信息
The text was updated successfully, but these errors were encountered:
No branches or pull requests
请将下面信息填写完整,便于我们快速解决问题,谢谢!
问题描述
请在此处详细的描述报错信息
我在GPU环境去运行PaddleNLP的taskflow,其中使用了UIE-X-Base模型,在taskflow中,我希望用fp16精度去提高预测速度
代码如下:
ie = Taskflow('information_extraction', schema=schema_obj,
batch_size=batch_size, model=‘uie-x-base’,
layout_analysis=True,precision='fp16')
在GPU环境安装了必要的依赖:onnxruntime-gpu onnx onnxconverter-common paddle2onnx
这是我试过的依赖的版本
onnx 1.17.0
onnxconverter-common 1.14.0
onnxruntime-gpu 1.14.1
paddle2onnx 1.3.1
paddlenlp 2.8.1 /2.7.0
paddleocr 2.9.1/2.7.0.0
paddlepaddle-gpu 3.0.0b2/2.6.2
但是初始化Taskflow的时候总是抛出module 'paddle2onnx' has no attribute 'command' 麻烦给个建议 怎么解决,多谢
更多信息 :
报错截图
其他信息
The text was updated successfully, but these errors were encountered: