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

'Unsqueeze' is not handled any converter handlers #893

Closed
paulbota opened this issue Oct 23, 2018 · 1 comment · Fixed by #900
Closed

'Unsqueeze' is not handled any converter handlers #893

paulbota opened this issue Oct 23, 2018 · 1 comment · Fixed by #900

Comments

@paulbota
Copy link

paulbota commented Oct 23, 2018

I try to run the code from the tutorial:

import torch, torchvision
from webdnn.frontend.pytorch import PyTorchConverter

model = torchvision.models.alexnet(pretrained=True)
dummy_input = torch.autograd.Variable(torch.randn(1, 3, 224, 224))
graph = PyTorchConverter().convert(model, dummy_input)

and I get the error: NotImplementedError: Operator 'Unsqueeze' is not handled any converter handlers.

Versions:
Python: 3.6.6
torch: 0.4.1
torchvision: 0.2.1
webdnn: 1.2.6
onnx: 1.3.0

@milhidaka
Copy link
Member

I supported latest pytorch's alexnet model.
Please try latest master branch.
Image preproceessing is different from other frameworks, please see
https://github.com/mil-tokyo/webdnn/blob/master/example/resnet/script.js#L65

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

Successfully merging a pull request may close this issue.

2 participants