Bas Aarts

Results 4 comments of Bas Aarts

hi @ball-boom. I've seen some regressions too after 0.4.17 regarding constants. for me applying `--skip-optimization eliminate_duplicate_initializer` made my failures disappear

same observation here: bad_alloc with opset >= 11, when using the python API (onnxsim.simpify) strange thing is that when I use the command line tool (onnxsim), the model optimizes just...

I also observed the the error is nondeterministic. Looking at [onnx2f](https://github.com/PINTO0309/onnx2tf), is seems like they cam e to the same conclusion:https://github.com/PINTO0309/onnx2tf/blob/794bd8699b55ea74c09411fd1d077448e02954aa/onnx2tf/onnx2tf.py#L505-L536 this looks like a serious issue @daquexian.