How to use the nnabla.functions.elu function in nnabla

def res_unit(x, scope):
        C = x.shape[1]
        with nn.parameter_scope(scope):
            with nn.parameter_scope('conv1'):
                h = F.elu(bn(PF.convolution(x, C / 2, (1, 1), with_bias=False)))
            with nn.parameter_scope('conv2'):
                h = F.elu(
                    bn(PF.convolution(h, C / 2, (3, 3), pad=(1, 1), with_bias=False)))
            with nn.parameter_scope('conv3'):
                h = bn(PF.convolution(h, C, (1, 1), with_bias=False))
        return F.elu(F.add2(h, x, inplace=True))
    # Conv1 --> 64 x 32 x 32

def res_unit(x, scope):
        C = x.shape[1]
        with nn.parameter_scope(scope):
            with nn.parameter_scope('conv1'):
                h = F.elu(bn(PF.convolution(x, C / 2, (1, 1), with_bias=False)))
            with nn.parameter_scope('conv2'):
                h = F.elu(
                    bn(PF.convolution(h, C / 2, (3, 3), pad=(1, 1), with_bias=False)))
            with nn.parameter_scope('conv3'):
                h = bn(PF.convolution(h, C, (1, 1), with_bias=False))
        return F.elu(F.add2(h, x, inplace=True))
    # Conv1 --> 64 x 32 x 32

def res_unit(x, scope):
        C = x.shape[1]
        with nn.parameter_scope(scope):
            with nn.parameter_scope('conv1'):
                h = F.elu(bn(PF.binary_connect_convolution(
                    x, C / 2, (1, 1), with_bias=False)))
            with nn.parameter_scope('conv2'):
                h = F.elu(
                    bn(PF.binary_connect_convolution(h, C / 2, (3, 3), pad=(1, 1), with_bias=False)))
            with nn.parameter_scope('conv3'):
                h = bn(PF.binary_connect_convolution(
                    h, C, (1, 1), with_bias=False))
        return F.elu(x + h)
    # Conv1 --> 64 x 32 x 32
    with nn.parameter_scope("conv1"):
        c1 = F.elu(
            bn(PF.binary_connect_convolution(image, 64, (3, 3), pad=(3, 3), with_bias=False)))
    # Conv2 --> 64 x 16 x 16
    c2 = F.max_pooling(res_unit(c1, "conv2"), (2, 2))
    # Conv3 --> 64 x 8 x 8
    c3 = F.max_pooling(res_unit(c2, "conv3"), (2, 2))
    # Conv4 --> 64 x 8 x 8
    c4 = res_unit(c3, "conv4")
    # Conv5 --> 64 x 4 x 4
    c5 = F.max_pooling(res_unit(c4, "conv5"), (2, 2))
    # Conv5 --> 64 x 4 x 4
    c6 = res_unit(c5, "conv6")
    pl = F.average_pooling(c6, (4, 4))
    with nn.parameter_scope("classifier"):
        y = bn(PF.binary_connect_affine(pl, 10))
    return y

def bn(x):
        # Batch normalization
        return PF.batch_normalization(x, batch_stat=not test)

    def upsample2(x, c):
        # Twise upsampling with deconvolution.
        return PF.deconvolution(x, c, kernel=(4, 4), pad=(1, 1), stride=(2, 2), with_bias=False)

    assert maxh / 4 > 0
    with nn.parameter_scope("gen"):
        # (Z, 1, 1) --> (256, 4, 4)
        with nn.parameter_scope("deconv1"):
            d1 = F.elu(bn(PF.deconvolution(z, maxh, (4, 4), with_bias=False)))
        # (256, 4, 4) --> (128, 8, 8)
        with nn.parameter_scope("deconv2"):
            d2 = F.elu(bn(upsample2(d1, maxh / 2)))
        # (128, 8, 8) --> (64, 16, 16)
        with nn.parameter_scope("deconv3"):
            d3 = F.elu(bn(upsample2(d2, maxh / 4)))
        # (64, 16, 16) --> (32, 28, 28)
        with nn.parameter_scope("deconv4"):
            # Convolution with kernel=4, pad=3 and stride=2 transforms a 28 x 28 map
            # to a 16 x 16 map. Deconvolution with those parameters behaves like an
            # inverse operation, i.e. maps 16 x 16 to 28 x 28.
            d4 = F.elu(bn(PF.deconvolution(
                d3, maxh / 8, (4, 4), pad=(3, 3), stride=(2, 2), with_bias=False)))
        # (32, 28, 28) --> (1, 28, 28)
        with nn.parameter_scope("conv5"):
            x = F.tanh(PF.convolution(d4, 1, (3, 3), pad=(1, 1)))
    if output_hidden:
        return x, [d1, d2, d3, d4]
    return x

def mnist_binary_connect_lenet_prediction(image, test=False):
    """
    Construct LeNet for MNIST (BinaryNet version).
    """
    with nn.parameter_scope("conv1"):
        c1 = PF.binary_connect_convolution(image, 16, (5, 5))
        c1 = PF.batch_normalization(c1, batch_stat=not test)
        c1 = F.elu(F.average_pooling(c1, (2, 2)))
    with nn.parameter_scope("conv2"):
        c2 = PF.binary_connect_convolution(c1, 16, (5, 5))
        c2 = PF.batch_normalization(c2, batch_stat=not test)
        c2 = F.elu(F.average_pooling(c2, (2, 2)))
    with nn.parameter_scope("fc3"):
        c3 = PF.binary_connect_affine(c2, 50)
        c3 = PF.batch_normalization(c3, batch_stat=not test)
        c3 = F.elu(c3)
    with nn.parameter_scope("fc4"):
        c4 = PF.binary_connect_affine(c3, 10)
        c4 = PF.batch_normalization(c4, batch_stat=not test)
    return c4

def downsample2(xx, c):
        return PF.convolution(xx, c, (3, 3), pad=(1, 1), stride=(2, 2), with_bias=False)

    assert maxh / 8 > 0
    with nn.parameter_scope("dis"):
        # (1, 28, 28) --> (32, 16, 16)
        with nn.parameter_scope("conv1"):
            c1 = F.elu(bn(PF.convolution(x, maxh / 8,
                                         (3, 3), pad=(3, 3), stride=(2, 2), with_bias=False)))
        # (32, 16, 16) --> (64, 8, 8)
        with nn.parameter_scope("conv2"):
            c2 = F.elu(bn(downsample2(c1, maxh / 4)))
        # (64, 8, 8) --> (128, 4, 4)
        with nn.parameter_scope("conv3"):
            c3 = F.elu(bn(downsample2(c2, maxh / 2)))
        # (128, 4, 4) --> (256, 4, 4)
        with nn.parameter_scope("conv4"):
            c4 = bn(PF.convolution(c3, maxh, (3, 3),
                                   pad=(1, 1), with_bias=False))
        # (256, 4, 4) --> (1,)
        with nn.parameter_scope("fc1"):
            f = PF.affine(c4, 1)
    if output_hidden:
        return f, [c1, c2, c3, c4]
    return f

(B, 1, 28, 28) outputs.
    """
    # Define shortcut functions
    def bn(x):
        # Batch normalization
        return PF.batch_normalization(x, batch_stat=not test)

    def upsample2(x, c):
        # Twice upsampling with deconvolution.
        return PF.deconvolution(x, c, kernel=(4, 4), pad=(1, 1), stride=(2, 2), with_bias=False)

    assert maxh / 4 > 0
    with nn.parameter_scope("gen"):
        # (Z, 1, 1) --> (256, 4, 4)
        with nn.parameter_scope("deconv1"):
            d1 = F.elu(bn(PF.deconvolution(z, maxh, (4, 4), with_bias=False)))
        # (256, 4, 4) --> (128, 8, 8)
        with nn.parameter_scope("deconv2"):
            d2 = F.elu(bn(upsample2(d1, maxh / 2)))
        # (128, 8, 8) --> (64, 16, 16)
        with nn.parameter_scope("deconv3"):
            d3 = F.elu(bn(upsample2(d2, maxh / 4)))
        # (64, 16, 16) --> (32, 28, 28)
        with nn.parameter_scope("deconv4"):
            # Convolution with kernel=4, pad=3 and stride=2 transforms a 28 x 28 map
            # to a 16 x 16 map. Deconvolution with those parameters behaves like an
            # inverse operation, i.e. maps 16 x 16 to 28 x 28.
            d4 = F.elu(bn(PF.deconvolution(
                d3, maxh / 8, (4, 4), pad=(3, 3), stride=(2, 2), with_bias=False)))
        # (32, 28, 28) --> (1, 28, 28)
        with nn.parameter_scope("conv5"):
            x = F.tanh(PF.convolution(d4, 1, (3, 3), pad=(1, 1)))

(B, 1, 28, 28) outputs.
    """
    # Define shortcut functions
    def bn(x):
        # Batch normalization
        return PF.batch_normalization(x, batch_stat=not test)

    def upsample2(x, c):
        # Twise upsampling with deconvolution.
        return PF.deconvolution(x, c, kernel=(4, 4), pad=(1, 1), stride=(2, 2), with_bias=False)

    assert maxh / 4 > 0
    with nn.parameter_scope("gen"):
        # (Z, 1, 1) --> (256, 4, 4)
        with nn.parameter_scope("deconv1"):
            d1 = F.elu(bn(PF.deconvolution(z, maxh, (4, 4), with_bias=False)))
        # (256, 4, 4) --> (128, 8, 8)
        with nn.parameter_scope("deconv2"):
            d2 = F.elu(bn(upsample2(d1, maxh / 2)))
        # (128, 8, 8) --> (64, 16, 16)
        with nn.parameter_scope("deconv3"):
            d3 = F.elu(bn(upsample2(d2, maxh / 4)))
        # (64, 16, 16) --> (32, 28, 28)
        with nn.parameter_scope("deconv4"):
            # Convolution with kernel=4, pad=3 and stride=2 transforms a 28 x 28 map
            # to a 16 x 16 map. Deconvolution with those parameters behaves like an
            # inverse operation, i.e. maps 16 x 16 to 28 x 28.
            d4 = F.elu(bn(PF.deconvolution(
                d3, maxh / 8, (4, 4), pad=(3, 3), stride=(2, 2), with_bias=False)))
        # (32, 28, 28) --> (1, 28, 28)
        with nn.parameter_scope("conv5"):
            x = F.tanh(PF.convolution(d4, 1, (3, 3), pad=(1, 1)))

with nn.parameter_scope("gen"):
        # (Z, 1, 1) --> (256, 4, 4)
        with nn.parameter_scope("deconv1"):
            d1 = F.elu(bn(PF.deconvolution(z, maxh, (4, 4), with_bias=False)))
        # (256, 4, 4) --> (128, 8, 8)
        with nn.parameter_scope("deconv2"):
            d2 = F.elu(bn(upsample2(d1, maxh / 2)))
        # (128, 8, 8) --> (64, 16, 16)
        with nn.parameter_scope("deconv3"):
            d3 = F.elu(bn(upsample2(d2, maxh / 4)))
        # (64, 16, 16) --> (32, 28, 28)
        with nn.parameter_scope("deconv4"):
            # Convolution with kernel=4, pad=3 and stride=2 transforms a 28 x 28 map
            # to a 16 x 16 map. Deconvolution with those parameters behaves like an
            # inverse operation, i.e. maps 16 x 16 to 28 x 28.
            d4 = F.elu(bn(PF.deconvolution(
                d3, maxh / 8, (4, 4), pad=(3, 3), stride=(2, 2), with_bias=False)))
        # (32, 28, 28) --> (1, 28, 28)
        with nn.parameter_scope("conv5"):
            x = F.tanh(PF.convolution(d4, 1, (3, 3), pad=(1, 1)))
    if output_hidden:
        return x, [d1, d2, d3, d4]
    return x