Katsuya Hyodo

I process input orders using a tool that I have created myself. However, I think the idea of adding an option to onnx-simplifier is great. :smile: - "Very simple NCHW...

duangenquan, AlexeyAB Thank you for such a wonderful tutorial. Please see the following if you wish. https://qiita.com/PINTO/items/b084fe3dc716c42e2867 https://qiita.com/PINTO/items/7f13fcb7c894c27691b2 It probably works because it uses the same IC. https://developer.movidius.com/

I have been considering implementing this for half a year, but it is hard to verify that the output of the converted DCNv2 OP is correct because onnxruntime does not...

- replace.json ```json { "format_version": 1, "operations": [ { "op_name": "Gather_1436", "param_target": "outputs", "param_name": "onnx::Concat_2347", "post_process_transpose_perm": [0,2,1] } ] } ``` - [experimental] convert ``` # 10 times onnxsim onnxsim...

I have confirmed that I can convert successfully with this tool I am creating. `onnx2tf` I am only interested in the transformation of the model and not in checking if...

There are significant changes in the combination of `opset=11` input values and attributes for onnx, so some opsets may work correctly and others may not. I think your point is...

The conversion has already been successful.

onnx2tf

I have already implemented all the optimization tricks that most engineers probably do not practice. You are probably already in a position to benefit from them.

As stated in the README of this repository, it seems to have been deprecated.  So I have started to create and test another tool by myself. If you don't...