Python mxnet.gluon.HybridBlock() Examples

def test_reshape_deconv():
    class Net(gluon.HybridBlock):
        def __init__(self, shape, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.reshape = shape
                self.conv0 = nn.Conv2DTranspose(64, (3, 3))

        def hybrid_forward(self, F, x):
            x_reshape = x.reshape(self.reshape)
            out = self.conv0(x_reshape)
            return out
    x = mx.nd.random.uniform(shape=(4, 16, 32, 32))
    shape = (4, 16, 64, -1)
    net = Net(shape)
    check_layer_forward_withinput(net, x) 

def test_slice_deconv_reshape_deconv():
    class Net(gluon.HybridBlock):
        def __init__(self, shape, slice, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.reshape = shape
                self.slice = slice
                self.conv0 = nn.Conv2DTranspose(32, (3, 3))
                self.conv1 = nn.Conv2DTranspose(96, (3, 3), strides=(2, 2))

        def hybrid_forward(self, F, x):
            x_slice = x.slice(begin=self.slice[0], end=self.slice[1])
            y = self.conv0(x_slice)
            "shape of y is (4, 32, 34, 34)"
            y_reshape = y.reshape(self.reshape)
            out = self.conv1(y_reshape)
            return out
    x = mx.nd.random.uniform(shape=(8, 32, 64, 64))
    shape = (4, 64, 34, -1)
    slice = [(4, 0, 0, 0), (8, 16, 32, 32)]
    net = Net(shape, slice)
    check_layer_forward_withinput(net, x) 

def test_reshape_conv_reshape_conv():
    class Net(gluon.HybridBlock):
        def __init__(self, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.conv0 = nn.Conv2D(64, (3, 3))
                self.conv1 = nn.Conv2D(128, (3, 3))

        def hybrid_forward(self, F, x):
            x_reshape = x.reshape((0, 0, 128, 32))
            y = self.conv0(x_reshape)
            "spatial shape of y is (62, 62)"
            y_reshape = y.reshape((0, 0, 124, 31))
            out = self.conv1(y_reshape)
            return out
    x = mx.nd.random.uniform(shape=(4, 3, 64, 64))
    net = Net()
    check_layer_forward_withinput(net, x) 

def test_slice_activation():
    class Net(gluon.HybridBlock):
        def __init__(self, act, slice, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.slice = slice
                self.act = nn.Activation(act)

        def hybrid_forward(self, F, x):
            x_slice = x.slice(begin=self.slice[0], end=self.slice[1])
            out = self.act(x_slice)
            return out

    acts = ["relu", "sigmoid", "tanh", "softrelu"]
    for act in acts:
        x = mx.nd.random.uniform(-1, 1, shape=(8, 32, 64, 64))
        slice = [(0, 16, 32, 32), (4, 32, 64, 64)]
        net = Net(act, slice)
        check_layer_forward_withinput(net, x) 

def test_reshape_activation():
    class Net(gluon.HybridBlock):
        def __init__(self, act, shape, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.reshape = shape
                self.act = nn.Activation(act)

        def hybrid_forward(self, F, x):
            x_reshape = x.reshape(self.reshape)
            out = self.act(x_reshape)
            return out
    acts = ["relu", "sigmoid", "tanh", "softrelu"]
    for act in acts:
        x = mx.nd.random.uniform(-1, 1, shape=(4, 16, 32, 32))
        shape = (4, 32, 32, -1)
        net = Net(act, shape)
        check_layer_forward_withinput(net, x) 

def test_reshape_activation_reshape_activation():
    class Net(gluon.HybridBlock):
        def __init__(self, act0, act1, shape, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.reshape = shape
                self.act0 = nn.Activation(act0)
                self.act1 = nn.Activation(act1)

        def hybrid_forward(self, F, x):
            x_reshape = x.reshape(self.reshape[0])
            y = self.act0(x_reshape)
            y_reshape = y.reshape(self.reshape[1])
            out = self.act1(y_reshape)
            return out
    acts = ["relu", "sigmoid", "tanh", "softrelu"]
    for idx0, act0 in enumerate(acts):
        for idx1, act1 in enumerate(acts):
            if idx1 == idx0:
                continue
            x = mx.nd.random.uniform(-1, 1, shape=(4, 16, 32, 32))
            shape = [(4, 32, 32, -1), (4, 32, 16, -1)]
            net = Net(act0, act1, shape)
            check_layer_forward_withinput(net, x) 

def test_conv2d_16c():
    chn_list = [16, 256]
    kernel_list = [1, 3]
    kernel_list.append(224)
    batch_size = 4
    class Net(gluon.HybridBlock):
        def __init__(self,
                     chn_num,
                     kernel,
                     **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.conv0 = gluon.nn.Conv2D(chn_num, (kernel, kernel))

        def hybrid_forward(self, F, x):
            out = self.conv0(x)
            return out

    x = mx.nd.random.uniform(-1.0, 1.0, shape=(batch_size, 3, 224, 224))
    for i in range(len(chn_list)):
        for j in range(len(kernel_list)):
            net = Net(chn_list[i], kernel_list[j])
            check_layer_forward_withinput(net, x) 

def darknet53(**kwargs):
    """Darknet v3 53 layer network.
    Reference: https://arxiv.org/pdf/1804.02767.pdf.

    Parameters
    ----------
    norm_layer : object
        Normalization layer used (default: :class:`mxnet.gluon.nn.BatchNorm`)
        Can be :class:`mxnet.gluon.nn.BatchNorm` or :class:`mxnet.gluon.contrib.nn.SyncBatchNorm`.
    norm_kwargs : dict
        Additional `norm_layer` arguments, for example `num_devices=4`
        for :class:`mxnet.gluon.contrib.nn.SyncBatchNorm`.

    Returns
    -------
    mxnet.gluon.HybridBlock
        Darknet network.

    """
    return get_darknet('v3', 53, **kwargs) 

def test_constant():
    class Test(gluon.HybridBlock):
        def __init__(self, **kwargs):
            super(Test, self).__init__(**kwargs)
            self.value = np.asarray([[1,2], [3,4]])
            self.const = self.params.get_constant('const', self.value)

        def hybrid_forward(self, F, x, const):
            return x + const

    test = Test()
    test.initialize()
    trainer = gluon.Trainer(test.collect_params(), 'sgd',
                            {'learning_rate': 1.0, 'momentum': 0.5})

    with mx.autograd.record():
        x = mx.nd.ones((2,2))
        x.attach_grad()
        y = test(x)
        y.backward()

    trainer.step(1)

    assert (test.const.data().asnumpy() == test.value).all()
    assert (x.grad.asnumpy() == 1).all() 

def test_slice_conv_reshape_conv():
    class Net(gluon.HybridBlock):
        def __init__(self, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.conv0 = nn.Conv2D(64, (3, 3))
                self.conv1 = nn.Conv2D(128, (3, 3))

        def hybrid_forward(self, F, x):
            x_slice = x.slice(begin=(0, 0, 1, 1), end=(4, 16, 33, 33))
            y = self.conv0(x_slice)
            "shape of y is (4, 64, 30, 30)"
            y_reshape = y.reshape((0, 0, 60, 15))
            out = self.conv1(y_reshape)
            return out

    x = mx.nd.random.uniform(shape=(4, 32, 64, 64))
    net = Net()
    check_layer_forward_withinput(net, x) 

def test_reshape_dense():
    class Net(gluon.HybridBlock):
        def __init__(self, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                channel0 = np.random.randint(1, 17)
                self.dense0 = nn.Dense(channel0)

        def hybrid_forward(self, F, x):
            x_reshape = x.reshape((8, 64, 128, -1))
            out = self.dense0(x_reshape)
            return out

    x = mx.nd.random.uniform(shape=(4, 32, 64, 64))
    net = Net()
    check_layer_forward_withinput(net, x) 

def test_slice_dense():
    class Net(gluon.HybridBlock):
        def __init__(self, slice, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                channel0 = np.random.randint(1, 17)
                self.dense0 = nn.Dense(channel0)
                self.slice = slice

        def hybrid_forward(self, F, x):
            x_slice = x.slice(begin=tuple(self.slice[0]),
                              end=tuple(self.slice[1]))
            out = self.dense0(x_slice)
            return out

    x = mx.nd.random.uniform(shape=(16, 32, 64, 64))
    slice = [[0, 16, 0, 0], [4, 32, 32, 32]]
    net = Net(slice)
    check_layer_forward_withinput(net, x) 

def test_slice_dense_slice_dense():
    class Net(gluon.HybridBlock):
        def __init__(self, slice, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                channel0 = 32
                channel1 = np.random.randint(1, 17)
                self.dense0 = nn.Dense(channel0)
                self.dense1 = nn.Dense(channel1)
                self.slice = slice

        def hybrid_forward(self, F, x):
            x_slice = x.slice(begin=tuple(self.slice[0]), end=tuple(self.slice[1]))
            y = self.dense0(x_slice)
            y_slice = y.slice(begin=(1, 0), end=(3, 10))
            out = self.dense1(y_slice)
            return out

    x = mx.nd.random.uniform(shape=(16, 32, 64, 64))
    slice = [[0, 16, 0, 0], [4, 32, 32, 32]]
    net = Net(slice)
    check_layer_forward_withinput(net, x) 

def test_reshape_dense_slice_dense():
    class Net(gluon.HybridBlock):
        def __init__(self, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                channel0 = 64
                channel1 = np.random.randint(1, 17)
                self.dense0 = nn.Dense(channel0)
                self.dense1 = nn.Dense(channel1)

        def hybrid_forward(self, F, x):
            x_reshape = x.reshape((4, 16, 128, 32))
            y = self.dense0(x_reshape)
            y_slice = y.slice(begin=(1, 32), end=(3, 64))
            out = self.dense1(y_slice)
            return out

    x = mx.nd.random.uniform(shape=(4, 16, 64, 64))
    net = Net()
    check_layer_forward_withinput(net, x) 

def test_reshape_conv_slice_conv():
    """
    This test will test gluon Conv2d computation with ndarray reshape and slice
    """
    class Net(gluon.HybridBlock):
        def __init__(self, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.conv0 = nn.Conv2D(16, (3, 3))
                self.conv1 = nn.Conv2D(32, (3, 3))

        def hybrid_forward(self, F, x):
            x_reshape = x.reshape((0, 0, 64, 16))
            y = self.conv0(x_reshape)
            "shape of y is (4, 16, 62, 14)"
            y_slice = y.slice(begin=(0, 0, 0, 0), end=(2, 16, 14, 14))
            out = self.conv1(y_slice)
            return out
    x = mx.nd.random.uniform(shape=(4, 3, 32, 32))
    net = Net()
    check_layer_forward_withinput(net, x) 

def test_slice_deconv():
    class Net(gluon.HybridBlock):
        def __init__(self, slice, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.slice = slice
                self.conv0 = nn.Conv2DTranspose(64, (3, 3))

        def hybrid_forward(self, F, x):
            x_slice = x.slice(begin=self.slice[0], end=self.slice[1])
            out = self.conv0(x_slice)
            return out
    x = mx.nd.random.uniform(shape=(8, 32, 64, 64))
    slice = [(0, 16, 0, 0), (4, 32, 32, 32)]
    net = Net(slice)
    check_layer_forward_withinput(net, x) 

def plot_mxboard(block, logdir='./logs'):
    """Plot network to visualize internal structures.

    Parameters
    ----------
    block : mxnet.gluon.HybridBlock
        A hybridizable network to be visualized.
    logdir : str
        The directory to save.

    """
    try:
        from mxboard import SummaryWriter
    except ImportError:
        print('mxboard is required. Please install via `pip install mxboard` ' +
              'or refer to https://github.com/awslabs/mxboard.')
        raise
    data = mx.sym.var('data')
    sym = block(data)
    if isinstance(sym, tuple):
        sym = mx.sym.Group(sym)
    with SummaryWriter(logdir=logdir) as sw:
        sw.add_graph(sym)
    usage = '`tensorboard --logdir={} --host=127.0.0.1 --port=8888`'.format(logdir)
    print('Log saved. Use: {} to visualize it'.format(usage)) 

def test_reshape_deconv_reshape_deconv():
    class Net(gluon.HybridBlock):
        def __init__(self, shape, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.reshape = shape
                self.conv0 = nn.Conv2DTranspose(32, (3, 3))
                self.conv1 = nn.Conv2DTranspose(64, (3, 3), strides=(2, 2))

        def hybrid_forward(self, F, x):
            x_reshape = x.reshape(self.reshape[0])
            y = self.conv0(x_reshape)
            "shape of y is (4, 32, 66, 18)"
            y_reshape = y.reshape(self.reshape[1])
            out = self.conv1(y_reshape)
            return out
    x = mx.nd.random.uniform(shape=(4, 16, 32, 32))
    shape = [(4, 16, 64, -1), (4, 32, 33, -1)]
    net = Net(shape)
    check_layer_forward_withinput(net, x) 

def hybrid_forward(self, F, samples, matches, refs):
        """HybridBlock, handle multi batch correctly

        Parameters
        ----------
        samples: (B, N), value +1 (positive), -1 (negative), 0 (ignore)
        matches: (B, N), value range [0, M)
        refs: (B, M), value range [0, num_fg_class), excluding background

        Returns
        -------
        targets: (B, N), value range [0, num_fg_class + 1), including background

        """
        # samples (B, N) (+1, -1, 0: ignore), matches (B, N) [0, M), refs (B, M)
        # reshape refs (B, M) -> (B, 1, M) -> (B, N, M)
        refs = F.broadcast_like(F.reshape(refs, (0, 1, -1)), matches, lhs_axes=1, rhs_axes=1)
        # ids (B, N, M) -> (B, N), value [0, M + 1), 0 reserved for background class
        target_ids = F.pick(refs, matches, axis=2) + 1
        # samples 0: set ignore samples to ignore_label
        targets = F.where(samples > 0.5, target_ids, F.ones_like(target_ids) * self._ignore_label)
        # samples -1: set negative samples to 0
        targets = F.where(samples < -0.5, F.zeros_like(targets), targets)
        return targets 

def test_reshape_deconv_slice_deconv():
    class Net(gluon.HybridBlock):
        def __init__(self, shape, slice, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.reshape = shape
                self.slice = slice
                self.conv0 = nn.Conv2DTranspose(32, (3, 3))
                self.conv1 = nn.Conv2DTranspose(64, (3, 3), strides=(2, 2))

        def hybrid_forward(self, F, x):
            x_reshape = x.reshape(self.reshape)
            y = self.conv0(x_reshape)
            "shape of y is (4, 32, 66, 18)"
            y_slice = y.slice(begin=self.slice[0], end=self.slice[1])
            out = self.conv1(y_slice)
            return out
    x = mx.nd.random.uniform(shape=(4, 16, 32, 32))
    shape = (4, 16, 64, -1)
    slice = [(0, 0, 0, 0), (2, 16, 16, 16)]
    net = Net(shape, slice)
    check_layer_forward_withinput(net, x) 

def test_reshape_batchnorm_slice_batchnorm():
    class Net(gluon.HybridBlock):
        def __init__(self, shape, slice, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.conv0 = nn.Conv2D(128, (1, 1))
                self.bn0 = nn.BatchNorm()
                self.bn1 = nn.BatchNorm()
                self.reshape = shape
                self.slice = slice

        def hybrid_forward(self, F, x):
            x_in = self.conv0(x)
            x_reshape = x_in.reshape(self.reshape)
            y = self.bn0(x_reshape)
            y_slice = y.slice(begin=tuple(self.slice[0]), end=tuple(self.slice[1]))
            out = self.bn1(y_slice)
            return out

    x = mx.nd.random.uniform(shape=(4, 32, 64, 64))
    slice = [[0, 0, 0, 0], [2, 64, 32, 32]]
    shape = (4, 64, 64, -1)
    net = Net(shape, slice)
    check_layer_forward_withinput(net, x) 

def test_slice_batchnorm_reshape_batchnorm():
    class Net(gluon.HybridBlock):
        def __init__(self, shape, slice, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.conv0 = nn.Conv2D(128, (1, 1))
                self.bn0 = nn.BatchNorm()
                self.bn1 = nn.BatchNorm()
                self.reshape = shape
                self.slice = slice

        def hybrid_forward(self, F, x):
            x_in = self.conv0(x)
            x_slice = x_in.slice(begin=tuple(self.slice[0]), end=tuple(self.slice[1]))
            y = self.bn0(x_slice)
            y_reshape = y.reshape(self.reshape)
            out = self.bn1(y_reshape)
            return out

    x = mx.nd.random.uniform(shape=(16, 128, 256, 256))
    slice = [[0, 0, 0, 0], [4, 32, 32, 32]]
    shape = (1, 128, 64, -1)
    net = Net(shape, slice)
    check_layer_forward_withinput(net, x) 

def test_slice_batchnorm_slice_batchnorm():
    class Net(gluon.HybridBlock):
        def __init__(self, slice, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.conv0 = nn.Conv2D(128, (1, 1))
                self.bn0 = nn.BatchNorm()
                self.bn1 = nn.BatchNorm()
                self.slice = slice

        def hybrid_forward(self, F, x):
            x_in = self.conv0(x)
            x_slice = x_in.slice(begin=tuple(self.slice[0][0]), end=tuple(self.slice[0][1]))
            y = self.bn0(x_slice)
            y_slice = y.slice(begin=tuple(self.slice[1][0]), end=tuple(self.slice[1][1]))
            out = self.bn1(y_slice)
            return out

    x = mx.nd.random.uniform(shape=(16, 128, 256, 256))
    slice = [[[0, 0, 0, 0], [4, 32, 32, 32]], [[0, 0, 0, 0], [2, 64, 16, 16]]]
    net = Net(slice)
    check_layer_forward_withinput(net, x) 

def test_slice_batchnorm():
    class Net(gluon.HybridBlock):
        def __init__(self, slice, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.conv0 = nn.Conv2D(128, (1, 1))
                self.bn0 = nn.BatchNorm()
                self.slice = slice

        def hybrid_forward(self, F, x):
            x_in = self.conv0(x)
            x_slice = x_in.slice(begin=tuple(self.slice[0]),
                              end=tuple(self.slice[1]))
            out = self.bn0(x_slice)
            return out

    x = mx.nd.random.uniform(shape=(16, 128, 256, 256))
    slice = [[0, 0, 0, 0], [4, 32, 32, 32]]
    net = Net(slice)
    check_layer_forward_withinput(net, x) 

def test_reshape_batchnorm():
    class Net(gluon.HybridBlock):
        def __init__(self, shape, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.conv0 = nn.Conv2D(96, (1, 1))
                self.bn0 = nn.BatchNorm()
                self.reshape = shape

        def hybrid_forward(self, F, x):
            x_in = self.conv0(x)
            x_reshape = x_in.reshape(self.reshape)
            out = self.bn0(x_reshape)
            return out

    x = mx.nd.random.uniform(shape=(4, 32, 64, 64))
    shape = (4, 64, 64, -1)
    net = Net(shape)
    check_layer_forward_withinput(net, x) 

def test_slice_dense_reshape_dense():
    class Net(gluon.HybridBlock):
        def __init__(self, slice, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                channel0 = np.random.randint(1, 17)
                channel1 = np.random.randint(1, 17)
                self.dense0 = nn.Dense(channel0)
                self.dense1 = nn.Dense(channel1)
                self.slice = slice

        def hybrid_forward(self, F, x):
            x_slice = x.slice(begin=tuple(self.slice[0]), end=tuple(self.slice[1]))
            y = self.dense0(x_slice)
            y_reshape = y.reshape((1, -1))
            out = self.dense1(y_reshape)
            return out

    x = mx.nd.random.uniform(shape=(16, 32, 64, 64))
    slice = [[0, 16, 0, 0], [4, 32, 32, 32]]
    net = Net(slice)
    check_layer_forward_withinput(net, x) 

def test_reshape_activation_slice_activation():
    class Net(gluon.HybridBlock):
        def __init__(self, act0, act1, shape, slice, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.reshape = shape
                self.slice = slice
                self.act0 = nn.Activation(act0)
                self.act1 = nn.Activation(act1)

        def hybrid_forward(self, F, x):
            x_reshape = x.reshape(self.reshape)
            y = self.act0(x_reshape)
            y_slice = y.slice(begin=self.slice[0], end=self.slice[1])
            out = self.act1(y_slice)
            return out
    acts = ["relu", "sigmoid", "tanh", "softrelu"]
    for idx0, act0 in enumerate(acts):
        for idx1, act1 in enumerate(acts):
            if idx1 == idx0:
                continue
            x = mx.nd.random.uniform(-1, 1, shape=(4, 16, 32, 32))
            shape = (4, 32, 32, -1)
            slice = [(0, 0, 0, 0), (2, 16, 16, 16)]
            net = Net(act0, act1, shape, slice)
            check_layer_forward_withinput(net, x) 

def test_slice_before_conv():
    class Net(gluon.HybridBlock):
        """
        test Net
        """
        def __init__(self, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.conv0 = nn.Conv2D(4, (3, 3))
                self.conv1 = nn.Conv2D(4, (3, 3))

        def hybrid_forward(self, F, x, *args, **kwargs):
            x_slice = x.slice(begin=(0, 0, 0, 0), end=(2, 4, 10, 10))
            y = self.conv0(x_slice)
            y_slice = y.slice(begin=(1, 0, 2, 2), end=(2, 1, 7, 7))
            out = self.conv1(y_slice)
            return out
    x = mx.nd.random.uniform(shape=(2, 10, 10, 10))
    x.attach_grad()
    net = Net()
    net.collect_params().initialize()
    with mx.autograd.record():
        out1 = net(x)
    out1.backward()
    dx1 = x.grad
    net.hybridize()
    with mx.autograd.record():
        out2 = net(x)
    out2.backward()
    mx.test_utils.assert_almost_equal(dx1.asnumpy(), x.grad.asnumpy(), rtol=1e-5, atol=1e-6)
    mx.test_utils.assert_almost_equal(out1.asnumpy(), out2.asnumpy(), rtol=1e-5, atol=1e-6) 

def test_slice_reshape_before_conv():
    class Net(gluon.HybridBlock):
        """
        test Net
        """
        def __init__(self, **kwargs):
            super(Net, self).__init__(**kwargs)
            with self.name_scope():
                self.conv0 = nn.Conv2D(4, (3, 3))
                self.conv1 = nn.Conv2D(4, (3, 3))

        def hybrid_forward(self, F, x, *args, **kwargs):
            x_slice = x.slice(begin=(0, 0, 0, 0), end=(2, 4, 8, 9))
            y = self.conv0(x_slice)
            y_reshape = y.reshape((0, 0, 14, 3))
            out = self.conv1(y_reshape)
            return out
    x = mx.nd.random.uniform(shape=(2, 10, 10, 10))
    x.attach_grad()
    net = Net()
    net.collect_params().initialize()
    with mx.autograd.record():
        out1 = net(x)
    out1.backward()
    dx1 = x.grad
    net.hybridize()
    with mx.autograd.record():
        out2 = net(x)
    out2.backward()
    mx.test_utils.assert_almost_equal(dx1.asnumpy(), x.grad.asnumpy(), rtol=1e-5, atol=1e-6)
    mx.test_utils.assert_almost_equal(out1.asnumpy(), out2.asnumpy(), rtol=1e-5, atol=1e-6) 

def yolo3_darknet53_coco(pretrained_base=True, pretrained=False,
                         norm_layer=BatchNorm, norm_kwargs=None, **kwargs):
    """YOLO3 multi-scale with darknet53 base network on COCO dataset.
    Parameters
    ----------
    pretrained_base : boolean
        Whether fetch and load pretrained weights for base network.
    pretrained : bool or str
        Boolean value controls whether to load the default pretrained weights for model.
        String value represents the hashtag for a certain version of pretrained weights.
    norm_layer : object
        Normalization layer used (default: :class:`mxnet.gluon.nn.BatchNorm`)
        Can be :class:`mxnet.gluon.nn.BatchNorm` or :class:`mxnet.gluon.contrib.nn.SyncBatchNorm`.
    norm_kwargs : dict
        Additional `norm_layer` arguments, for example `num_devices=4`
        for :class:`mxnet.gluon.contrib.nn.SyncBatchNorm`.
    Returns
    -------
    mxnet.gluon.HybridBlock
        Fully hybrid yolo3 network.
    """
    from ...data import COCODetection
    pretrained_base = False if pretrained else pretrained_base
    base_net = darknet53(
        pretrained=pretrained_base, norm_layer=norm_layer, norm_kwargs=norm_kwargs, **kwargs)
    stages = [base_net.features[:15], base_net.features[15:24], base_net.features[24:]]
    anchors = [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]]
    strides = [8, 16, 32]
    classes = COCODetection.CLASSES
    return get_yolov3(
        'darknet53', stages, [512, 256, 128], anchors, strides, classes, 'coco',
        pretrained=pretrained, norm_layer=norm_layer, norm_kwargs=norm_kwargs, **kwargs)