Open PPakalns opened 3 years ago
Hey, just for info, I've runned a custom Bert Model on onnxruntime using HF tokenizer on Python and Rust and the result are identical. I've runned it on a personal onnxruntime v1.8 with GPU which could be the reason of the fix.
My code if it can help: https://github.com/haixuanTao/bert-onnx-rs-pipeline
It looks like somewhere these bindings are adding error to float output.
When using native C++ onnxruntime API in the output for yolov3 onnx model I receive
Using python and native C++ onnxruntime API:
Using onnxruntime-rs API:
These results are approximately the same, but you can see the errors, which are pretty huge!
I even tried to compile onnxruntime with different backends and enable them with modifying this crate.
Tried
download
andsystem
onnxruntimes, with and without GPU, with custom backend, etc.