Tom Wildenhain

The primary graph of interest is __inference___call___110 which calls __inference__preprocess_88 (the later can also be called independently)  The signatures can be found using the saved model cli with `saved_model_cli...

Hi @WassimBouatay, can you try again using the latest tf2onnx? `pip install --upgrade tf2onnx` I think we might have fixed a similar issue a while back. If that fails please...

#1543 features another model using this op. ksizes = [1, 3, 3, 1], rates = [1, 1, 1, 1], strides = [1, 1, 1, 1], padding = 'SAME'/'VALID'

If we want to do an onnx op, could we do a conv with an identity kernel?

I think you should be able to move the M and C values of 2304 and 256 to the batch dimension, do the conv with a simple [1, 1, 3,...

Perfect. Actually if reshape sees a -1 in the shape it will dump all the remaining dimensions into there, and a 0 indicates to keep that dim the same. Since...

@spillerrec it would be fantastic if you could add support for this op in tf2onnx. Add a handler for ExtractImagePatches in nn.py https://github.com/onnx/tensorflow-onnx/blob/master/tf2onnx/onnx_opset/nn.py You can copy CTCGreedyDecoder as a template....

@spillerrec Just checking if you've had a chance to work on this. Happy to help if you are stuck.

Yes please share a zip with the saved model and the onnx model. Normally the model produces correct results if it converts without error but we do have some some...

Hey @juliakorovsky can you upload a saved model and onnx file so we can reproduce this? I'm thinking optimization of Select/Where ops may be coming up here. Also double-check using...