You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello,
I have noticed that the output of an h3 layer, when provided the same input tensor, is different when use_fast_fftconv=True versus when use_fast_fftconv=False. Similarly, I have tested this on the fftconv_func and fftconv_ref functions (in fftconv.py) and they give different outputs when given the same input arguments. Is this behavior expected? Is fftconv_func performing any approximation that causes this relatively large Euclidean distance between the two outputs?
Thanks in advance for your help.
The text was updated successfully, but these errors were encountered:
Can you provide more details about the differences in output you're seeing? It may be slight numerical errors due to fp32/fp16/bf16.
We have a test in tests/ops that tests for numerical errors - you can run it via pytest tests/ops/test_fftconv.py - can you run that and see if all the tests pass?
Thanks so much for your reply. After running tests/ops/test_fftconv.py, I received 3488 passed, 672 skipped.
Here is the code snippet I use to measure the difference in outputs:
Yes, that is within a standard numerical error that can come from two slightly different but mathematically equivalent implementations of the same operation, or from converting between fp32/fp16 and bf16.
Hello,
I have noticed that the output of an h3 layer, when provided the same input tensor, is different when use_fast_fftconv=True versus when use_fast_fftconv=False. Similarly, I have tested this on the fftconv_func and fftconv_ref functions (in fftconv.py) and they give different outputs when given the same input arguments. Is this behavior expected? Is fftconv_func performing any approximation that causes this relatively large Euclidean distance between the two outputs?
Thanks in advance for your help.
The text was updated successfully, but these errors were encountered: