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

Demo multiPose fail, report inputChannel: 225, batch:1, width:225, height:3. Input data channel may be mismatch with filter channel count #2859

Open
bin913 opened this issue May 6, 2024 · 2 comments

Comments

@bin913
Copy link

bin913 commented May 6, 2024

平台: ubuntu20.04 intel cpu


Github版本: ba4ecd9792f76c21061215342722fe052f5faf5b

编译方式:
mkdir build && cd build
cmake .. -DMNN_BUILD_DEMO=ON -DMNN_BUILD_CONVERTER=ON -DMNN_BUILD_TORCH=ON
make -j4

报错信息:
originalWidth:225
originalHeight:225
originalChannel:4
The device support i8sdot:0, support fp16:0, support i8mm: 0
	**Tensor shape**: 1, 225, 3, 225, 
Error for compute convolution shape, inputCount:3, outputCount:24, KH:3, KW:3, group:1
inputChannel: 225, batch:1, width:225, height:3. Input data channel may be mismatch with filter channel count
Compute Shape Error for MobilenetV1/add

@bin913 bin913 changed the title Demo multiPose fail, report inputChannel: 225, batch:1, width:225, height:3. Input data channel may be mismatch with filter channel count Demo multiPose fail, report Input data channel may be mismatch with filter channel count May 6, 2024
@bin913 bin913 changed the title Demo multiPose fail, report Input data channel may be mismatch with filter channel count Demo multiPose fail, report inputChannel: 225, batch:1, width:225, height:3. Input data channel may be mismatch with filter channel count May 6, 2024
@zyg519
Copy link

zyg519 commented May 8, 2024

mnnNet->resizeTensor(input, {1, 3, targetHeight, targetWidth});

调整一下维度顺序试试

@bin913
Copy link
Author

bin913 commented May 11, 2024

我调整维度顺序之后,测试通过了,多谢

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