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

升级版本,从 1.4 到 1.5 版本后,报错卷积层 dilation 尺寸不对 #188

Open
AllentDan opened this issue Jul 12, 2023 · 3 comments

Comments

@AllentDan
Copy link

E load_onnx: RuntimeError: Shape inference error(s): (op_type:Conv, node name: Conv_0): [ShapeInferenceError] Attribute dilations has incorrect size
E load_onnx: (op_type:Relu, node name: Relu_1): [TypeInferenceError] Input 0 expected to have type but instead is null
E load_onnx: (op_type:MaxPool, node name: MaxPool_2): [TypeInferenceError] Input 0 expected to have type but instead is nu

模型是 resnet

@yuyun2000
Copy link

佬,dilations的限制是[1,32],其次首层输入也有限制,根据不同的平台也有不同的限制,你可以看详细的op说明,最下面有补充,你这是改参数了吧,不然咋报错

@AllentDan
Copy link
Author

没改参数,修好了,open-mmlab/mmdeploy#2278
rknn-toolkit 1.5+ can not pass input output info, which is weird 亲测

@yuyun2000
Copy link

佬太强,太强佬

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