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

Implement LRN #310

Open

salvacarrion opened this issue Dec 1, 2021 · 1 comment

Assignees

Labels

enhancement Hard priority

Contributor

salvacarrion commented Dec 1, 2021 •

edited

Loading

This layer is used in many early DNNs such as AlexNet, GoogLeNet, Inception, etc. so we need to implement it to support these models through ONNX.

For now, we have two workarounds to be made:

Option 1.: Bypass this layer in ONNX showing a warning
Option 2.: Replace it with BatchNorm where its parameters are all ones and zeros

Info:

salvacarrion assigned chavicoski

salvacarrion added enhancement Hard priority labels

salvacarrion assigned salvacarrion and unassigned chavicoski

Contributor Author

salvacarrion commented Dec 10, 2021

I think it is supported by cuDNN: https://docs.nvidia.com/deeplearning/cudnn/api/index.html#cudnnSetLRNDescriptor

chavicoski added a commit that referenced this issue


          Added Bypass layer to skip the LRN layer (issue #310)

d8b8a4e

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