Re:Convert Apple NeuralHash model for CSAM Detection to ONNX
by tvirosi on Wednesday August 18, 2021 @10:18AM
(#28221245)
I've tried inference on the python version of onnx and it usually varies between hitting a OOM limit (while with TF it works fine) to being an order of magnitude slower. Even if the codebase is still being changed I don't see much reason for people to use it other than as a convenient distribution format.
[ Parent
| on HN ]
Re:Convert Apple NeuralHash model for CSAM Detection to ONNX
by akhundelar on Wednesday August 18, 2021 @11:02AM
(#28222013)
Interesting, I did not encounter such discrepancies in my work with these tools.
There could be multiple reasons for the degraded performance:
- Are we comparing apples to apples here (heh), e.g. ResNet-50 vs ResNet-50?
- Was the ONNX model ported from TF? There are known issues with that path (https://onnxruntime.ai/docs/how-to/tune-performance.html#my-...)
- Have you tried tuning an execution provider for your specific target platform?(https://onnxruntime.ai/docs/reference/execution-providers/#s...)