Skip to content

Use the PyTorch BatchNorm folding instead of a handwritten converter when possible #31

New issue
New issue
Closed
Closed
Use the PyTorch BatchNorm folding instead of a handwritten converter when possible#31
Labels
component: loweringIssues re: The lowering / preprocessing passesfeature requestNew feature or requestgood first issueGood for newcomershelp wantedExtra attention is neededpriority: high
Milestone
 
v0.1.0
@narendasan

Description

@narendasan
narendasan
opened on Apr 1, 2020

We currently use a handwritten converter for batch norm which fuses the operations into a single convolution. It would be easier to use the _jit_pass_fold_convbn pass in lowering instead where we can.

Metadata

Metadata

Assignees

No one assigned

    Labels

    component: loweringIssues re: The lowering / preprocessing passesfeature requestNew feature or requestgood first issueGood for newcomershelp wantedExtra attention is neededpriority: high

    Type

    No type

    Projects

    No projects

    Milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions