Only image inputs are supported for import using 'importONNXNetwork'

15 visualizaciones (últimos 30 días)
PRAMOD BACHHAV
PRAMOD BACHHAV el 23 de Ag. de 2019
Respondida: yanqi liu el 17 de En. de 2022
Hello,
My question in regarding the add-on 'importONNXNetwork'.
I am unable to load a ONNX model in MATLAB (2018b). The model is trained in PyTorch.
Input to the model is a vector and not an image.
I get following error: 'Only image inputs are supported for import'.
I am wondering if this is because MATLAB add-on doesn't (yet) support loading of ONNX models with non-image inputs.
Please let me know. Thanks in advance.
Regards,
Pramod

Respuestas (3)

matteo baigura
matteo baigura el 1 de Feb. de 2020
Editada: matteo baigura el 1 de Feb. de 2020
Same problem, if you are right that's simply ridicolous

Josiah Wai
Josiah Wai el 17 de En. de 2022
Editada: Josiah Wai el 17 de En. de 2022
I also had this problem and was able to get around it by reshaping the onnx input vector.
  1. To export from pytorch to onnx, follow the steps at https://pytorch.org/tutorials/advanced/super_resolution_with_onnxruntime.html However, before running the torch.onnx.export command, set the shape of your input vector x. In my case, each input sample vector has size 33, so I did: x = torch.randn(1,1,33, requires_grad=True)
  2. Import to Matlab
net = importONNXNetwork(modelfile, 'OutputLayerType', 'regression')
x = rand(33,1)
y = predict(net, x)

yanqi liu
yanqi liu el 17 de En. de 2022
yes,sir,may be transfer data to cell and save as mat file,then use reshape to modify data dimension

Categorías

Más información sobre Deep Learning Toolbox en Help Center y File Exchange.

Productos

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by