def Convolution()

in utils/symbol/symbol_octconv.py [0:0]

• 24 lines of code
• 25 McCabe index (conditional complexity)

def Convolution(data, num_filter, kernel, stride=(1, 1), pad=(0, 0), num_group=1, no_bias=True, name=None):
    data_h, data_l = data if type(data) is tuple else (data, None)
    num_high, num_low = num_filter if type(num_filter) is tuple else (num_filter, 0)

    assert num_high >= 0 and num_low >= 0 
    assert stride == (1, 1) or stride == (2, 2), "stride = {} is not supported yet".format(stride)

    data_h2l, data_h2h, data_l2l, data_l2h = None, None, None, None
    depthwise = True if num_filter == num_group else False
    
    '''processing high frequency group'''
    if data_h is not None:
        # High -> High
        data_h = mx.sym.Pooling(data=data_h, pool_type="avg", kernel=(2, 2), pad=(0, 0), stride=(2, 2)) if stride == (2, 2) else data_h
        data_h2h = mx.sym.Convolution(data=data_h, num_filter=num_high, kernel=kernel, stride=(1, 1), pad=pad, num_group=min(num_high, num_group), no_bias=no_bias, name=('%s-h2h' % name)) if num_high > 0 else None
        # High -> Low
        if not depthwise:
            data_h2l = mx.sym.Pooling(data=data_h, pool_type="avg", kernel=(2, 2), pad=(0, 0), stride=(2, 2)) if (num_low > 0) else data_h
            data_h2l = mx.sym.Convolution(data=data_h2l, num_filter=num_low, kernel=kernel, stride=(1, 1), pad=pad, num_group=min(num_low, num_group), no_bias=no_bias, name=('%s-h2l' % name)) if num_low > 0 else None

    '''processing low frequency group'''
    if data_l is not None:
        # Low -> Low
        data_l2l = mx.sym.Pooling(data=data_l, pool_type="avg", kernel=(2, 2), pad=(0, 0), stride=(2, 2)) if (num_low > 0 and stride == (2, 2)) else data_l
        data_l2l = mx.sym.Convolution(data=data_l2l, num_filter=num_low, kernel=kernel, stride=(1, 1), pad=pad, num_group=min(num_low, num_group), no_bias=True, name=('%s-l2l' % name)) if num_low > 0 else None
        # Low -> High
        if not depthwise:
            data_l2h = mx.sym.Convolution(data=data_l, num_filter=num_high, kernel=kernel, stride=(1, 1), pad=pad, num_group=min(num_high, num_group), no_bias=True, name=('%s-l2h' % name)) if num_high > 0 else None
            data_l2h = mx.sym.UpSampling(data_l2h, scale=2, sample_type="nearest", num_args=1) if (num_high > 0 and stride == (1, 1)) else data_l2h

    '''you can force to disable the interaction paths'''
    # data_h2l = None if (data_h2h is not None) and (data_l2l is not None) else data_h2l
    # data_l2h = None if (data_h2h is not None) and (data_l2l is not None) else data_l2h

    output = ElementWiseSum(*[(data_h2h, data_h2l), (data_l2h, data_l2l)], name=name)
    
    # squeeze output (to be backward compatible)
    return output[0] if output[1] is None else output