You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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]
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]
and in GraphSage can we set the epsilon to 1e-5 or 1e-7 ?
The text was updated successfully, but these errors were encountered: