Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Still not similar enough when running with an ONNX model trained with PyTorch (F32) #3

Open
phudtran opened this issue Aug 30, 2024 · 0 comments

Comments

@phudtran
Copy link
Owner

phudtran commented Aug 30, 2024

Signal after STFT -> model inference -> ISTFT

Rust:

[
0.9909163339142713, 
1.9712342556337927, 
2.953786843060888, 
3.921420771696601,
4.952314387002861, 
5.907277470915773, 
6.979393529935473, 
7.859013433858505, 
8.866255643188893, 
9.70119035560396
]

PyTorch

[
0.99496907, 
1.9647579, 
2.9484708, 
3.9149268, 
4.950324, 
5.9061565, 
6.9777083, 
7.859473, 
8.867544, 
9.710843
], 
@phudtran phudtran changed the title Still not accurate enough when running with an ONNX model trained with PyTorch (F32) Still not similar enough when running with an ONNX model trained with PyTorch (F32) Aug 30, 2024
@phudtran phudtran pinned this issue Oct 6, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant