Skip to content

Wrong dimensions for Avg-Pool layer #11

@tobiascz

Description

@tobiascz

I think there is a small mistake in the model of the i3d.

self.layers[end_point] = nn.AvgPool3d(kernel_size=[8, 7, 7], stride=(1, 1, 1))

In the paper QuVadis Action Recognition this is actuall 2,7,7 not 8,7,7.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions