Function `convert` failed with layer `LayerNormalization`. However, `BatchNormalization` succeeds.

[klae01]

This is ipython code (at colab) which makes an error.

Code

# !pip install tensorflow==2.6.4 onnx==1.12.0 onnx2torch git+https://github.com/onnx/tensorflow-onnx

import tensorflow as tf
import onnx

from onnx2torch import convert

with tf.device("/cpu:0"):
    tf_model = tf.keras.Sequential()
    tf_model.add(tf.keras.layers.Input((123,)))
    tf_model.add(tf.keras.layers.LayerNormalization())
    tf.keras.models.save_model(
        tf_model,
        "model.tf",
        overwrite=True,
        include_optimizer=False,
        save_format=None,
        signatures=None,
        options=None,
        save_traces=True
    )
!python -m tf2onnx.convert --saved-model model.tf --output model.onnx --opset 11 --verbose
onnx_model = onnx.load("model.onnx")
encoder_pth = convert(onnx_model)

Error Message

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
[<ipython-input-2-2bc3e427f014>](https://localhost:8080/#) in <module>()
     22 get_ipython().system('python -m tf2onnx.convert --saved-model model.tf --output model.onnx --opset 11 --verbose')
     23 onnx_model = onnx.load("model.onnx")
---> 24 encoder_pth = convert(onnx_model)

1 frames
[/usr/local/lib/python3.7/dist-packages/onnx2torch/converter.py](https://localhost:8080/#) in convert(onnx_model_or_path, save_input_names, attach_onnx_mapping)
    107         )
    108 
--> 109         torch_module, onnx_mapping = converter(onnx_node, onnx_graph)
    110         if attach_onnx_mapping:
    111             setattr(torch_module, 'onnx_mapping', onnx_mapping)

[/usr/local/lib/python3.7/dist-packages/onnx2torch/node_converters/batch_norm.py](https://localhost:8080/#) in _(node, graph)
     24 def _(node: OnnxNode, graph: OnnxGraph) -> OperationConverterResult:
     25     scale_value_name = node.input_values[1]
---> 26     scale = graph.initializers[scale_value_name]
     27     scale = scale.to_torch()
     28 

KeyError: 'StatefulPartitionedCall/sequential_1/layer_normalization_1/ones:0'

[niobeus]

Hello! I think the reason is LayerNorm is supported in 17 opset only. In your case LayerNorm is represented by multiple nodes and one of them is BatchNormalization. Onnx2torch expects scale, bias, input_mean, input_var attributes of BatchNorm to be in graph.initializers, but in your case they are dynamic (i.e. outputs of previous nodes). We will try to resolve your issue as soon as possible.