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

Test SINGA ONNX Converter #1

Open
moazreyad opened this issue Jan 9, 2018 · 0 comments
Open

Test SINGA ONNX Converter #1

moazreyad opened this issue Jan 9, 2018 · 0 comments

Comments

@moazreyad
Copy link
Owner

moazreyad commented Jan 9, 2018

We need to try the ONNX converter with AlexNet

The ONNX converter is here:

https://github.com/moazreyad/incubator-singa/tree/onnx/tool/onnx

Steps:

  1. Get the AlexNet from Pytorch:

http://pytorch.org/docs/master/onnx.html

from torch.autograd import Variable
import torch.onnx
import torchvision

dummy_input = Variable(torch.randn(10, 3, 224, 224)).cuda()
model = torchvision.models.alexnet(pretrained=True).cuda()
torch.onnx.export(model, dummy_input, "alexnet.proto", verbose=True)
  1. Convert to SINGA using the ONNX converter :

onnx_to_singa file.proto

  1. Test the converted model in SINGA and report the issues to be fixed.
moazreyad pushed a commit that referenced this issue Aug 24, 2019
moazreyad pushed a commit that referenced this issue Feb 29, 2020
changes EXPECT_EQ to EXPECT_NEAR
moazreyad pushed a commit that referenced this issue Aug 17, 2020
moazreyad pushed a commit that referenced this issue Aug 27, 2020
Update from apache:dev branch
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

1 participant