MCPcopy Create free account
hub / github.com/MTLab/MorphMLP / __init__

Method __init__

slowfast/models/video_model_builder.py:112–153  ·  view source on GitHub ↗

Args: dim_in (int): the channel dimension of the input. fusion_conv_channel_ratio (int): channel ratio for the convolution used to fuse from Fast pathway to Slow pathway. fusion_kernel (int): kernel size of the convolution used to fuse

(
        self,
        dim_in,
        fusion_conv_channel_ratio,
        fusion_kernel,
        alpha,
        eps=1e-5,
        bn_mmt=0.1,
        inplace_relu=True,
        norm_module=nn.BatchNorm3d,
    )

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 1

__init__Method · 0.45

Tested by

no test coverage detected