Python chainer.links方法代碼示例

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def make_q_func(self, env):
        obs_size = env.observation_space.low.size
        hidden_size = 64
        return iqn.StatelessRecurrentImplicitQuantileQFunction(
            psi=chainerrl.links.StatelessRecurrentSequential(
                L.Linear(obs_size, hidden_size),
                F.relu,
                L.NStepRNNTanh(1, hidden_size, hidden_size, 0),
            ),
            phi=chainerrl.links.Sequence(
                chainerrl.agents.iqn.CosineBasisLinear(32, hidden_size),
                F.relu,
            ),
            f=L.Linear(hidden_size, env.action_space.n,
                       initialW=chainer.initializers.LeCunNormal(1e-1)),
        ) 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def block_embed(embed, x, dropout=0.):
    """Embedding function followed by convolution

    Args:
        embed (callable): A :func:`~chainer.functions.embed_id` function
            or :class:`~chainer.links.EmbedID` link.
        x (:class:`~chainer.Variable` or :class:`numpy.ndarray` or \
        :class:`cupy.ndarray`): Input variable, which
            is a :math:`(B, L)`-shaped int array. Its first dimension
            :math:`(B)` is assumed to be the *minibatch dimension*.
            The second dimension :math:`(L)` is the length of padded
            sentences.
        dropout (float): Dropout ratio.

    Returns:
        ~chainer.Variable: Output variable. A float array with shape
        of :math:`(B, N, L, 1)`. :math:`(N)` is the number of dimensions
        of word embedding.

    """
    e = embed(x)
    e = F.dropout(e, ratio=dropout)
    e = F.transpose(e, (0, 2, 1))
    e = e[:, :, :, None]
    return e 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def convert_onnx_chainer_convolution2d(onnx_graph: 'ONNXGraph', node: 'nodes.NodeCall'):
    chainer_inst = node.func.owner.inst  # type: chainer.links.Convolution2D

    ksize = oc.size2d(chainer_inst.ksize)
    stride = oc.size2d(chainer_inst.stride)
    ps = oc.size2d(chainer_inst.pad)
    pads = ps + ps

    x = oc.ONNXValue(onnx_graph, node.args.get_value('x'))
    o = oc.ONNXValue(onnx_graph, node.outputs[0])
    w = oc.ONNXValue(onnx_graph, chainer_inst.W)
    b = None

    if chainer_inst.b is not None:
        b = oc.ONNXValue(onnx_graph, chainer_inst.b)

    onnx_graph.add_node(
        'Conv',
        [x, w] + ([] if b is None else [b]),
        [o],
        str(node.lineprop),
        kernel_shape=ksize,
        pads=pads,
        strides=stride) 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def convert_onnx_chainer_convolutionnd(onnx_graph: 'ONNXGraph', node: 'nodes.NodeCall'):
    chainer_inst = node.func.owner.inst  # type: chainer.links.ConvolutionND

    nd = chainer_inst.W.ndim - 2
    ksize = oc.size_nd(chainer_inst.ksize, nd)
    stride = oc.size_nd(chainer_inst.stride, nd)
    ps = oc.size_nd(chainer_inst.pad, nd)
    pads = ps + ps

    x = oc.ONNXValue(onnx_graph, node.args.get_value('x'))
    o = oc.ONNXValue(onnx_graph, node.outputs[0])
    w = oc.ONNXValue(onnx_graph, chainer_inst.W)
    b = None

    if chainer_inst.b is not None:
        b = oc.ONNXValue(onnx_graph, chainer_inst.b)

    onnx_graph.add_node(
        'Conv',
        [x, w] + ([] if b is None else [b]),
        [o],
        str(node.lineprop),
        kernel_shape=ksize,
        pads=pads,
        strides=stride) 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def convert_onnx_chainer_batch_normalization(onnx_graph: 'ONNXGraph', node: 'nodes.NodeCall'):
    chainer_inst = node.func.owner.inst  # type: chainer.links.BatchNormalization

    assert(chainer_inst.axis is None)  # not support yet

    x = oc.ONNXValue(onnx_graph, node.args.get_value('x'))
    o = oc.ONNXValue(onnx_graph, node.outputs[0])

    gamma = oc.ONNXValue(onnx_graph, chainer_inst.gamma)
    beta = oc.ONNXValue(onnx_graph, chainer_inst.beta)
    avg_mean = oc.ONNXValue(onnx_graph, chainer_inst.avg_mean, [node, 'mean'])
    avg_var = oc.ONNXValue(onnx_graph, chainer_inst.avg_var, [node, 'var'])
    eps = chainer_inst.eps
    momentum = chainer_inst.decay

    onnx_graph.add_node(
        'BatchNormalization',
        [x, gamma, beta, avg_mean, avg_var],
        [o],
        str(node.lineprop),
        epsilon=eps,
        momentum=momentum) 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def convert_onnx_chainer_EmbedID(onnx_graph: 'ONNXGraph', node: 'nodes.NodeCall'):
    chainer_inst = node.func.owner.inst  # type: chainer.links.EmbedID

    n_vocab = chainer_inst.W.shape[0]
    n_out = chainer_inst.W.shape[1]

    w = oc.ONNXValue(onnx_graph, chainer_inst.W)

    parser = oc.NodeParse()
    parser.add_def('x', oc.ParseType.In)
    parser.parse(onnx_graph, node)

    x = parser.get('x').create_tensor(node.lineprop)

    onnx_graph.add_node(
        'Gather',
        [w, x],
        [node.outputs[0]],
        str(node.lineprop)) 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def __init__(self, comm, in_channels, out_channels, ksize, pad=1):
        super(Block, self).__init__()
        with self.init_scope():
            if comm.size <= in_channels:
                self.conv = ParallelConvolution2D(comm,
                                                  in_channels,
                                                  out_channels,
                                                  ksize,
                                                  pad=pad,
                                                  nobias=True)
            else:
                self.conv = chainer.links.Convolution2D(in_channels,
                                                        out_channels,
                                                        ksize,
                                                        pad=pad,
                                                        nobias=True)
            self.bn = L.BatchNormalization(out_channels) 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def test_convolution(self):
        self.init_func()
        self.assertEqual(len(self.func.layers), 1)
        f = self.func.l1
        self.assertIsInstance(f, links.Convolution2D)
        for i in range(3):  # 3 == group
            in_slice = slice(i * 4, (i + 1) * 4)  # 4 == channels
            out_slice = slice(i * 2, (i + 1) * 2)  # 2 == num / group
            w = f.W.data[out_slice, in_slice]
            numpy.testing.assert_array_equal(
                w.flatten(), range(i * 32, (i + 1) * 32))

        numpy.testing.assert_array_equal(
            f.b.data, range(6))

        self.call(['x'], ['y'])
        self.mock.assert_called_once_with(self.inputs[0]) 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def test_deconvolution(self):
        self.init_func()
        self.assertEqual(len(self.func.layers), 1)
        f = self.func.l1
        self.assertIsInstance(f, links.Deconvolution2D)
        for i in range(3):  # 3 == group
            in_slice = slice(i * 4, (i + 1) * 4)  # 4 == channels
            out_slice = slice(i * 2, (i + 1) * 2)  # 2 == num / group
            w = f.W.data[out_slice, in_slice]
            numpy.testing.assert_array_equal(
                w.flatten(), range(i * 32, (i + 1) * 32))

        numpy.testing.assert_array_equal(
            f.b.data, range(12))

        self.call(['x'], ['y'])
        self.mock.assert_called_once_with(self.inputs[0]) 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def __init__(self, n_layers, n_units, width=3, dropout=0.2):
        super(ConvGLUDecoder, self).__init__()
        links = [('l{}'.format(i + 1),
                  ConvGLU(n_units, width=width,
                          dropout=dropout, nopad=True))
                 for i in range(n_layers)]
        for link in links:
            self.add_link(*link)
        self.conv_names = [name for name, _ in links]
        self.width = width

        init_preatt = VarInNormal(1.)
        links = [('preatt{}'.format(i + 1),
                  L.Linear(n_units, n_units, initialW=init_preatt))
                 for i in range(n_layers)]
        for link in links:
            self.add_link(*link)
        self.preatt_names = [name for name, _ in links] 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def __init__(self):
        super(Darknet53Extractor, self).__init__()

        # Darknet53
        self.append(Conv2DBNActiv(32, 3, pad=1, activ=_leaky_relu))
        for k, n_block in enumerate((1, 2, 8, 8, 4)):
            self.append(Conv2DBNActiv(
                32 << (k + 1), 3, stride=2, pad=1, activ=_leaky_relu))
            for _ in range(n_block):
                self.append(ResidualBlock(
                    Conv2DBNActiv(32 << k, 1, activ=_leaky_relu),
                    Conv2DBNActiv(32 << (k + 1), 3, pad=1, activ=_leaky_relu)))

        # additional links
        for i, n in enumerate((512, 256, 128)):
            if i > 0:
                self.append(Conv2DBNActiv(n, 1, activ=_leaky_relu))
            self.append(Conv2DBNActiv(n, 1, activ=_leaky_relu))
            self.append(Conv2DBNActiv(n * 2, 3, pad=1, activ=_leaky_relu))
            self.append(Conv2DBNActiv(n, 1, activ=_leaky_relu))
            self.append(Conv2DBNActiv(n * 2, 3, pad=1, activ=_leaky_relu))
            self.append(Conv2DBNActiv(n, 1, activ=_leaky_relu)) 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def __init__(self):
        super(Darknet19Extractor, self).__init__()

        # Darknet19
        for k, n_conv in enumerate((1, 1, 3, 3, 5, 5)):
            for i in range(n_conv):
                if i % 2 == 0:
                    self.append(
                        Conv2DBNActiv(32 << k, 3, pad=1, activ=_leaky_relu))
                else:
                    self.append(
                        Conv2DBNActiv(32 << (k - 1), 1, activ=_leaky_relu))

        # additional links
        self.append(Conv2DBNActiv(1024, 3, pad=1, activ=_leaky_relu))
        self.append(Conv2DBNActiv(1024, 3, pad=1, activ=_leaky_relu))
        self.append(Conv2DBNActiv(64, 1, activ=_leaky_relu))
        self.append(Conv2DBNActiv(1024, 3, pad=1, activ=_leaky_relu)) 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def block_embed(embed, x, dropout=0.0):
    """Embedding function followed by convolution

    Args:
        embed (callable): A :func:`~chainer.functions.embed_id` function
            or :class:`~chainer.links.EmbedID` link.
        x (:class:`~chainer.Variable` or :class:`numpy.ndarray` or \
        :class:`cupy.ndarray`): Input variable, which
            is a :math:`(B, L)`-shaped int array. Its first dimension
            :math:`(B)` is assumed to be the *minibatch dimension*.
            The second dimension :math:`(L)` is the length of padded
            sentences.
        dropout (float): Dropout ratio.

    Returns:
        ~chainer.Variable: Output variable. A float array with shape
        of :math:`(B, N, L, 1)`. :math:`(N)` is the number of dimensions
        of word embedding.

    """
    e = embed(x)
    e = F.dropout(e, ratio=dropout)
    e = F.transpose(e, (0, 2, 1))
    e = e[:, :, :, None]
    return e 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def __init__(self, out_dims=64, normalize_output=False, n_proxy=None):
        super(ModifiedGoogLeNet, self).__init__()
        # remove links and functions
        for name in [n for n in self._children if n.startswith('loss')]:
            self._children.remove(name)
            delattr(self, name)
        self.functions.pop('loss3_fc')
        self.functions.pop('prob')

        self.add_link('bn_fc', L.BatchNormalization(1024))
        self.add_link('fc', L.Linear(1024, out_dims))

        # For Proxy-NCA
        if isinstance(n_proxy, int) and n_proxy > 0:
            proxy = np.random.randn(n_proxy, out_dims).astype(np.float32)
            self.add_param('P', initializer=proxy)

        image_mean = np.array([123, 117, 104], dtype=np.float32)  # RGB
        self._image_mean = image_mean[None, :, None, None]
        self.normalize_output = normalize_output 

# 需要導入模塊: import chainer [as 別名]
# 或者: from chainer import links [as 別名]
def __init__(self, ksize, n_out, initializer):
        super(ConvBlock, self).__init__()
        pad_size = ksize // 2
        links = [('conv1', L.Convolution2D(None, n_out, ksize, pad=pad_size, initialW=initializer))]
        links += [('bn1', L.BatchNormalization(n_out))]
        for link in links:
            self.add_link(*link)
        self.forward = links