Open jeonghm9764 opened 2 years ago
I have tried to optimize a LeNet from https://github.com/ONNC/onnc-tutorial/blob/master/models/lenet/lenet.onnx There are Reshape operations that go into each Add operation after Conv op, representing bias addition, and they sure do have values.
However, after optimization, B parameter of Add operation is now all zeros, which means bias is now zero. This gives different outputs (and different accuracy) when run with onnxruntime. I do not think this is expected.
Thanks in advance.
I have tried to optimize a LeNet from https://github.com/ONNC/onnc-tutorial/blob/master/models/lenet/lenet.onnx There are Reshape operations that go into each Add operation after Conv op, representing bias addition, and they sure do have values.
However, after optimization, B parameter of Add operation is now all zeros, which means bias is now zero. This gives different outputs (and different accuracy) when run with onnxruntime. I do not think this is expected.
Thanks in advance.