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
Describe the bug
I have passed convolution output(block sharded, the pcc of convolution output is >0.99) to maxpool the operation is executed but the output of maxpool pcc is low(~0.055).
Describe the bug
I have passed convolution output(block sharded, the pcc of convolution output is >0.99) to maxpool the operation is executed but the output of maxpool pcc is low(~0.055).
To Reproduce
Steps to reproduce the behavior:
pytest tests/ttnn/integration_tests/yolov4/unit_test_maxpool.py
Expected behavior
To have a pcc>0.99
Please complete the following environment information:
Additional context
If we change the convolution layout from Block_sharded to Height_sharded the output of maxpool is >0.99.
The text was updated successfully, but these errors were encountered: