model = dict(
    type='Recognizer3D',
    backbone=dict(
        type='ResNet3dSlowOnly',
        depth=50,
        pretrained='https://download.pytorch.org/models/resnet50-11ad3fa6.pth',
        lateral=False,
        conv1_kernel=(1, 7, 7),
        conv1_stride_t=1,
        pool1_stride_t=1,
        inflate=(0, 0, 1, 1),
        norm_eval=False),
    cls_head=dict(
        type='I3DHead',
        in_channels=2048,
        num_classes=400,
        spatial_type='avg',
        dropout_ratio=0.5,
        average_clips='prob'),
    data_preprocessor=dict(
        type='ActionDataPreprocessor',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        format_shape='NCTHW'))