SaeHie Park
SaeHie Park
@chinhuang007 , #885 fails to convert to DWConv for the models I've been working... I'll try to find how to fix for this model and mine too... --> It was...
From `Default MaxPoolingOp only supports NHWC on device type CPU` error message, I think this is like https://github.com/onnx/onnx-tensorflow/issues/862 issue.
Maybe check https://github.com/onnx/onnx-tensorflow/issues/921#issuecomment-853471398 with installing master onnx-tf ``` pip install -e git+https://github.com/onnx/onnx-tensorflow.git#egg=onnx_tf ```
[Samsung/ONE](https://github.com/Samsung/ONE/) is using as importing ONNX models :)
#9190 is already fired but we need to (1) define group of optimization and (2) switchs of pass for each group.
> Is it for just one-optimize? or all passes? I don't understand the question. `one-import` just imports source model (tf, tflite, onnx, ...) to circle model. I don't know what...
> I thought that almost options are okay So I think it's okay to turn on all options If so, the default option supports all true options ONNX related NCHW...
The word `group` I mentioned needs to be changed to another word for approrpriate purpose.
> I asked this because of https://github.com/Samsung/ONE/pull/9190#issuecomment-1139398914 . @mhs4670go , can you clarify what you mean in the comment? and about `So I thought optimization could be included from one-import...