-
Notifications
You must be signed in to change notification settings - Fork 4
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
Addressing two more convtranspose usecases #308
base: feature/onnx-to-tosa
Are you sure you want to change the base?
Addressing two more convtranspose usecases #308
Conversation
@@ -763,6 +767,16 @@ bool ShouldDecomposeConvTransposeOpToPhasedConvs(Value convTransposeResult, | |||
padsShape == SmallVector<int64_t>{1, 1, 0, 0}) | |||
return true; | |||
} | |||
// Supports only with padding [0, 0, 0, 0] |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I am wondering if we can generalize this instead of hardcoding specific paddings and kernels
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
If the padding is of convT is changed to [ 1, 1, 1, 1], the conv outputs of conv2 get top and left garbage, requiring the slice. We have to handle the change in padding with a different decomposition.
If convT has [2,2,2,2] padding, the decomposition deviates both from [1,1,1,1] and [0,0,0,0]
Co-authored-by: Jonas Rickert <[email protected]>
Addressing below usecases