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.

Sign up for GitHub

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

Jump to bottom

ONNX integration between PyTorch and CNTK #5

Open
3 of 5 tasks
lext opened this issue Aug 14, 2018 · 4 comments
Open
3 of 5 tasks

ONNX integration between PyTorch and CNTK #5

lext opened this issue Aug 14, 2018 · 4 comments
Assignees
@jfrondel
Labels
enhancement New feature or request maintenance Something that will improve the maintenance in the future, e.g. CI
Milestone
Segmentation pipe...

Comments

@lext
Copy link

lext commented Aug 14, 2018 •
edited by jfrondel
Loading

  • Bilinear upsampling as a transposed convolution
  • BatchNorm Fusion
  • Compare the inference results (CNTK vs PyTorch)
  • Tiling strategy for large samples
  • Test VNet and UNet
@lext lext added the enhancement New feature or request label Aug 14, 2018
@lext lext added this to the Segmentation pipeline conversion milestone Aug 14, 2018
@lext lext added the maintenance Something that will improve the maintenance in the future, e.g. CI label Aug 14, 2018
@jfrondel
Copy link
Contributor

Upsampling has been added in 97eccdc

@jfrondel
Copy link
Contributor

Model weights are saved after bn fusion with pytorch. CNTK model loads fused weights.

@jfrondel
Copy link
Contributor

jfrondel commented Sep 3, 2018

Inference works almost identically between cntk and pytorch. Difference in the dice scores are in the 3rd and 4th decimal place. bn fusion was omitted from the model due to issues. Working inference was added in 96cf1da.

@jfrondel
Copy link
Contributor

jfrondel commented Sep 5, 2018

bn fusion was fixed in 2dbb59a.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@jfrondel jfrondel

Labels
enhancement New feature or request maintenance Something that will improve the maintenance in the future, e.g. CI
Projects
None yet
Milestone
Segmentation pipeline conversion
Development

No branches or pull requests
2 participants
@lext @jfrondel