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
and I don't have any. I thought that these are not ONNX operators and will be converted to other types by tf2onnx converter. Should I be using a special converter which preserves these operators? What am I missing?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi,
I am trying to run onnxruntime/python/tools/transformer/optimizer.py to get an Bert model in ONNX format optimized. My fused attention count is 0.
I noticed the optimizer is looking for SkipLayerNormalization and LayerNormalization nodes in my model:
https://github.com/microsoft/onnxruntime/blob/master/onnxruntime/python/tools/transformers/onnx_model_bert_tf.py#L284
and I don't have any. I thought that these are not ONNX operators and will be converted to other types by tf2onnx converter. Should I be using a special converter which preserves these operators? What am I missing?
Thanks in advance!
Beta Was this translation helpful? Give feedback.
All reactions