Python nn.Conv2D方法代碼示例

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
def __init__(self, inplanes, planes, stride=1, downsample=None, norm_layer=InstanceNorm):
        super(Bottleneck, self).__init__()
        self.expansion = 4
        self.downsample = downsample
        if self.downsample is not None:
            self.residual_layer = nn.Conv2D(in_channels=inplanes, 
                                            channels=planes * self.expansion,
                                            kernel_size=1, strides=(stride, stride))
        self.conv_block = nn.Sequential()
        with self.conv_block.name_scope():
            self.conv_block.add(norm_layer(in_channels=inplanes))
            self.conv_block.add(nn.Activation('relu'))
            self.conv_block.add(nn.Conv2D(in_channels=inplanes, channels=planes, 
                                 kernel_size=1))
            self.conv_block.add(norm_layer(in_channels=planes))
            self.conv_block.add(nn.Activation('relu'))
            self.conv_block.add(ConvLayer(planes, planes, kernel_size=3, 
                stride=stride))
            self.conv_block.add(norm_layer(in_channels=planes))
            self.conv_block.add(nn.Activation('relu'))
            self.conv_block.add(nn.Conv2D(in_channels=planes, 
                                 channels=planes * self.expansion, 
                                 kernel_size=1)) 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
def test_fill_shape_load():
    ctx = mx.context.current_context()
    net1 = nn.HybridSequential()
    with net1.name_scope():
        net1.add(nn.Conv2D(64, kernel_size=2, padding=1),
                 nn.BatchNorm(),
                 nn.Dense(10))
    net1.hybridize()
    net1.initialize(ctx=ctx)
    net1(mx.nd.ones((2,3,5,7), ctx))
    net1.save_parameters('net_fill.params')

    net2 = nn.HybridSequential()
    with net2.name_scope():
        net2.add(nn.Conv2D(64, kernel_size=2, padding=1),
                 nn.BatchNorm(),
                 nn.Dense(10))
    net2.hybridize()
    net2.initialize()
    net2.load_parameters('net_fill.params', ctx)
    assert net2[0].weight.shape[1] == 3, net2[0].weight.shape[1]
    assert net2[1].gamma.shape[0] == 64, net2[1].gamma.shape[0]
    assert net2[2].weight.shape[1] == 3072, net2[2].weight.shape[1] 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
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) 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
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) 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
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) 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
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) 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
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) 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
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) 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
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) 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
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) 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
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) 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
def test_mkldnn_engine_threading():
    net = gluon.nn.HybridSequential()
    with net.name_scope():
        net.add(gluon.nn.Conv2D(channels=32, kernel_size=3, activation=None))
    net.collect_params().initialize(ctx=mx.cpu())
    class Dummy(gluon.data.Dataset):
        def __len__(self):
            return 2
        def __getitem__(self, key):
            return key, np.ones((3, 224, 224)), np.ones((10, ))

    loader = gluon.data.DataLoader(Dummy(), batch_size=2, num_workers=1)

    X = (32, 3, 32, 32)
    # trigger mkldnn execution thread
    y = net(mx.nd.array(np.ones(X))).asnumpy()

    # Use Gluon dataloader to trigger different thread.
    # below line triggers different execution thread
    for _ in loader:
        y = net(mx.nd.array(np.ones(X))).asnumpy()
        # output should be 016711406 (non-mkldnn mode output)
        assert_almost_equal(y[0, 0, 0, 0], 0.016711406)
        break 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
def __init__(self):
        super(CellStem0, self).__init__()
        self.conv_1x1 = nn.HybridSequential()
        self.conv_1x1.add(nn.Activation(activation='relu'))
        self.conv_1x1.add(nn.Conv2D(42, 1, strides=1, use_bias=False))
        self.conv_1x1.add(nn.BatchNorm(epsilon=0.001, momentum=0.1))

        self.comb_iter_0_left = BranchSeparables(42, 42, 5, 2, 2)
        self.comb_iter_0_right = BranchSeparablesStem(96, 42, 7, 2, 3, bias=False)

        self.comb_iter_1_left = nn.MaxPool2D(pool_size=3, strides=2, padding=1)
        self.comb_iter_1_right = BranchSeparablesStem(96, 42, 7, 2, 3, bias=False)

        self.comb_iter_2_left = nn.AvgPool2D(pool_size=3, strides=2, padding=1)
        self.comb_iter_2_right = BranchSeparablesStem(96, 42, 5, 2, 2, bias=False)

        self.comb_iter_3_right = nn.AvgPool2D(pool_size=3, strides=1, padding=1)

        self.comb_iter_4_left = BranchSeparables(42, 42, 3, 1, 1, bias=False)
        self.comb_iter_4_right = nn.MaxPool2D(pool_size=3, strides=2, padding=1) 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
def _make_dense_layer(growth_rate, bn_size, dropout):
    new_features = nn.HybridSequential(prefix='')
    new_features.add(nn.BatchNorm())
    #new_features.add(nn.Activation('relu'))
    new_features.add(Act())
    new_features.add(nn.Conv2D(bn_size * growth_rate, kernel_size=1, use_bias=False))
    new_features.add(nn.BatchNorm())
    #new_features.add(nn.Activation('relu'))
    new_features.add(Act())
    new_features.add(nn.Conv2D(growth_rate, kernel_size=3, padding=1, use_bias=False))
    if dropout:
        new_features.add(nn.Dropout(dropout))

    out = gluon.contrib.nn.HybridConcurrent(axis=1, prefix='')
    out.add(gluon.contrib.nn.Identity())
    out.add(new_features)

    return out 

# 需要導入模塊: from mxnet.gluon import nn [as 別名]
# 或者: from mxnet.gluon.nn import Conv2D [as 別名]
def __init__(self, num_init_features, growth_rate, block_config,
                 bn_size=4, dropout=0, classes=1000, **kwargs):

        super(DenseNet, self).__init__(**kwargs)
        with self.name_scope():
            self.features = nn.HybridSequential(prefix='')
            self.features.add(nn.Conv2D(num_init_features, kernel_size=3,
                                        strides=1, padding=1, use_bias=False))
            self.features.add(nn.BatchNorm())
            self.features.add(nn.Activation('relu'))
            self.features.add(nn.MaxPool2D(pool_size=3, strides=2, padding=1))
            # Add dense blocks
            num_features = num_init_features
            for i, num_layers in enumerate(block_config):
                self.features.add(_make_dense_block(num_layers, bn_size, growth_rate, dropout, i+1))
                num_features = num_features + num_layers * growth_rate
                if i != len(block_config) - 1:
                    self.features.add(_make_transition(num_features // 2))
                    num_features = num_features // 2
            self.features.add(nn.BatchNorm())
            self.features.add(nn.Activation('relu'))
            #self.features.add(nn.AvgPool2D(pool_size=7))
            #self.features.add(nn.Flatten())

            #self.output = nn.Dense(classes)