[Feature] How to get flops of the MMRecognizer3D?

[wukurua]

What is the problem this feature will solve?

I want to test GFlops for RGBPoseConv3D (configs\skeleton\posec3d\rgbpose_conv3d\rgbpose_conv3d.py), but the current code doesn't seem to support MMRecognizer3D . Hope to have a section for testing the Multi-modal 3D recognizer model framework in tools/analysis_tools/get_flops.py.
By the way, If you know the params and GFlops of RGBPoseConv3D, or its input_shape, can anyone tell me about it?

def main():

    args = parse_args()

    if len(args.shape) == 1:
        input_shape = (1, 3, args.shape[0], args.shape[0])
    elif len(args.shape) == 2:
        input_shape = (1, 3) + tuple(args.shape)
    elif len(args.shape) == 4:
        # n, c, h, w = args.shape for 2D recognizer
        input_shape = tuple(args.shape)
    elif len(args.shape) == 5:
        # n, c, t, h, w = args.shape for 3D recognizer or
        # n, m, t, v, c = args.shape for GCN-based recognizer
        # n, v, t, m, c = args.shape for GCN-based recognizer
        input_shape = tuple(args.shape)
    else:
        raise ValueError('invalid input shape')

What is the feature?

get flops of the MMRecognizer3D

What alternatives have you considered?

No response

[Yangxinyee]

the same question here...