NotImplementedError: Converter is not implemented (OperationDescription(domain='', operation_type='GRU', version=14))

[ZM-J]

Example code:

import tensorflow as tf

X = tf.keras.layers.Input(shape=(60, 78),
                                name='factor')
x = X
y = tf.keras.layers.GRU(1,
                        return_sequences=True)(x)

model = tf.keras.models.Model(inputs=X,
                              outputs=y)

import tf2onnx
onnx_model_path = '/path/to/model.onnx'
model_proto, external_tensor_storage = tf2onnx.convert.from_keras(model, output_path=onnx_model_path)

import onnx
onnx_model = onnx.load(onnx_model_path)
pytorch_model = convert(onnx_model)

Moreover, I'm currently using tensorflow==2.10.0, pytorch==2.5.0 and torchvision==0.20.0.

[ZM-J]

This issue shall be relevant to #136