Skip to content

[torchlib] Impl aten::native_group_norm with onnx::GroupNormalization #1205

Open

Description

Saw in comment

    # Because onnx.GroupNorm() need size=group for weight and bias
    # But the torch's aten function's input need size=channel, the size mismatched
    # So we have to use onnx.InstanceNorm() to simulate

and previous discussion #644 (comment).

Reviving the thread to see if something can be done to use ONNX GroupNorm. The current workaround with InstanceNorm produces way more nodes which are not ideal for performance.

E.g.:

image

cc @justinchuby @xiaowuhu

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Assignees

No one assigned

    Labels

    topic: torch_libRelated to the torch/aten function lib in development

    Type

    No type

    Projects

    No projects

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions