Skip to content
New issue

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

AINODE 模型部署 #13745

Open
YWzzq opened this issue Oct 12, 2024 · 1 comment
Open

AINODE 模型部署 #13745

YWzzq opened this issue Oct 12, 2024 · 1 comment

Comments

@YWzzq
Copy link

YWzzq commented Oct 12, 2024

ainode部署模型需要model.pt与config.yaml文件,
1.model.pt文件就是直接torch.save()生成的吗?
2.我使用了dlnear生成了model.pt文件来测试是否生成正确model.pt,报错:
IoTDB> call inference(dlinear_example, "select s0,s1,s2,s3,s4,s5,s6 from root.eg.etth", window=head(96))
Msg: org.apache.iotdb.jdbc.IoTDBSQLException: 301: Error occurred while executing inference:[PytorchStreamReader failed locating file constants.pkl: file not found]

@CritasWang
Copy link
Collaborator

是否满足一下几点呢

AINode 支持的PyTorch 2.1.0、 2.2.0版本训练的模型,需避免使用2.2.0版本以上的特性。
AINode支持使用PyTorch JIT存储的模型,模型文件需要包含模型的参数和结构。
模型输入序列可以包含一列或多列,若有多列,需要和模型能力、模型配置文件对应。
模型的输入输出维度必须在config.yaml配置文件中明确定义。使用模型时,必须严格按照config.yaml配置文件中定义的输入输出维度。如果输入输出列数不匹配配置文件,将会导致错误。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants