You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@singa.apache.org by GitBox <gi...@apache.org> on 2020/05/29 06:58:15 UTC

[GitHub] [singa] joddiy edited a comment on pull request #712: Implemented superresolution model

joddiy edited a comment on pull request #712:
URL: https://github.com/apache/singa/pull/712#issuecomment-635797466


   > @joddiy the `inputs, ref_outputs = load_dataset(os.path.join('/tmp', 'super_resolution', 'test_data_set_0'))` gives the error, after some debugging, I think it is because the output_*.pb has the dims specified as 224 x 224 but it actually has 451584 size. Thus, it cannot resize itself. Could there be an error with the output_.pb file itself?
   
   Yes, you are right, I've checked the code, and it seems the error displays at this line:
   https://github.com/onnx/onnx/blob/master/onnx/numpy_helper.py#L55
   
   The output should be `672*672`, but it gives a shape of `224*224`, which incurs the error.
   
   It'd be fine you skip this verification, you can just use an image to show a demo inference.
   
   By the way, since you found this problem of their model, I guess you can submit an Issue at ONNX model zoo's repo.


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org