Hi,
I am trying to convert the 3 MTCNN models (PNet, RNet and Onet) from this repo:
https://github.com/timesler/facenet-pytorch/blob/master/models/mtcnn.py
Conversion for PNet worked fine, I was able to get the same output in Python / Pytorch and C++ / NP_SDK.
However, I was not able to get the same output after the conversion of RNet and ONet.
At first I suspected the issue was operations
As those operations are not supported, I replaced them by
Because they are defined as supported network layers in documentation
https://developer.qualcomm.com/sites/default/files/docs/snpe/network_lay...,
However, I am still not getting the right output when comparing Python / Pytorch vs C++ / NP_SDK.
What am I doing wrong ?
Thanks.
Please note that I export models in ONNX format using Pytorch and use the spne-onnx-to-dlc script for the conversion step.
Dear customer,
Interesting about your model as mentioned.
What's the SNPE version and platform you have tested? Regarding the onnx model accuracy, you need to convert the output tensor from NCHW(SNPE) to NHWC(onnx) and then go to your more progress.
BR.
Wei