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

adding a espilon value in LayerNorm in GraphSAGE model #122

Open
thegodone opened this issue May 18, 2024 · 0 comments
Open

adding a espilon value in LayerNorm in GraphSAGE model #122

thegodone opened this issue May 18, 2024 · 0 comments

Comments

@thegodone
Copy link
Contributor

In version kgcnn 3.1, I've got a strange error related to this error tensorflow/tensorflow#62607

Is it possible to set or expose in the configs layernorm epsilon parameter in order to change it dynamically in GraphLayerNorm and LayerNorm ?

No registered '_MklLayerNorm' OpKernel for 'GPU' devices compatible with node {{node model/graph_layer_normalization/layer_normalization/add}}
. Registered: device='CPU'; T in [DT_BFLOAT16]
device='CPU'; T in [DT_FLOAT]

 [[model/graph_layer_normalization/layer_normalization/add]] [Op:__inference_test_function_10733]

and in GraphSage can we set the epsilon to 1e-5 or 1e-7 ?

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