Python lasagne.layers.FlattenLayer() Examples

def create_network():
    l = 1000
    pool_size = 5
    test_size1 = 13
    test_size2 = 7
    test_size3 = 5
    kernel1 = 128
    kernel2 = 128
    kernel3 = 128
    layer1 = InputLayer(shape=(None, 1, 4, l+1024))
    layer2_1 = SliceLayer(layer1, indices=slice(0, l), axis = -1)
    layer2_2 = SliceLayer(layer1, indices=slice(l, None), axis = -1)
    layer2_3 = SliceLayer(layer2_2, indices = slice(0,4), axis = -2)
    layer2_f = FlattenLayer(layer2_3)
    layer3 = Conv2DLayer(layer2_1,num_filters = kernel1, filter_size = (4,test_size1))
    layer4 = Conv2DLayer(layer3,num_filters = kernel1, filter_size = (1,test_size1))
    layer5 = Conv2DLayer(layer4,num_filters = kernel1, filter_size = (1,test_size1))
    layer6 = MaxPool2DLayer(layer5, pool_size = (1,pool_size))
    layer7 = Conv2DLayer(layer6,num_filters = kernel2, filter_size = (1,test_size2))
    layer8 = Conv2DLayer(layer7,num_filters = kernel2, filter_size = (1,test_size2))
    layer9 = Conv2DLayer(layer8,num_filters = kernel2, filter_size = (1,test_size2))
    layer10 = MaxPool2DLayer(layer9, pool_size = (1,pool_size))
    layer11 = Conv2DLayer(layer10,num_filters = kernel3, filter_size = (1,test_size3))
    layer12 = Conv2DLayer(layer11,num_filters = kernel3, filter_size = (1,test_size3))
    layer13 = Conv2DLayer(layer12,num_filters = kernel3, filter_size = (1,test_size3))
    layer14 = MaxPool2DLayer(layer13, pool_size = (1,pool_size))
    layer14_d = DenseLayer(layer14, num_units= 256)
    layer3_2 = DenseLayer(layer2_f, num_units = 128)
    layer15 = ConcatLayer([layer14_d,layer3_2])
    layer16 = DropoutLayer(layer15,p=0.5)
    layer17 = DenseLayer(layer16, num_units=256)
    network = DenseLayer(layer17, num_units= 2, nonlinearity=softmax)
    return network


#random search to initialize the weights 

def create_network():
    l = 1000
    pool_size = 5
    test_size1 = 13
    test_size2 = 7
    test_size3 = 5
    kernel1 = 128
    kernel2 = 128
    kernel3 = 128
    layer1 = InputLayer(shape=(None, 1, 4, l+1024))
    layer2_1 = SliceLayer(layer1, indices=slice(0, l), axis = -1)
    layer2_2 = SliceLayer(layer1, indices=slice(l, None), axis = -1)
    layer2_3 = SliceLayer(layer2_2, indices = slice(0,4), axis = -2)
    layer2_f = FlattenLayer(layer2_3)
    layer3 = Conv2DLayer(layer2_1,num_filters = kernel1, filter_size = (4,test_size1))
    layer4 = Conv2DLayer(layer3,num_filters = kernel1, filter_size = (1,test_size1))
    layer5 = Conv2DLayer(layer4,num_filters = kernel1, filter_size = (1,test_size1))
    layer6 = MaxPool2DLayer(layer5, pool_size = (1,pool_size))
    layer7 = Conv2DLayer(layer6,num_filters = kernel2, filter_size = (1,test_size2))
    layer8 = Conv2DLayer(layer7,num_filters = kernel2, filter_size = (1,test_size2))
    layer9 = Conv2DLayer(layer8,num_filters = kernel2, filter_size = (1,test_size2))
    layer10 = MaxPool2DLayer(layer9, pool_size = (1,pool_size))
    layer11 = Conv2DLayer(layer10,num_filters = kernel3, filter_size = (1,test_size3))
    layer12 = Conv2DLayer(layer11,num_filters = kernel3, filter_size = (1,test_size3))
    layer13 = Conv2DLayer(layer12,num_filters = kernel3, filter_size = (1,test_size3))
    layer14 = MaxPool2DLayer(layer13, pool_size = (1,pool_size))
    layer14_d = DenseLayer(layer14, num_units= 256)
    layer3_2 = DenseLayer(layer2_f, num_units = 128)
    layer15 = ConcatLayer([layer14_d,layer3_2])
    #layer16 = DropoutLayer(layer15,p=0.5)
    layer17 = DenseLayer(layer15, num_units=256)
    network = DenseLayer(layer17, num_units= 1, nonlinearity=None)
    return network


#random search to initialize the weights 

def build_convpool_conv1d(input_vars, nb_classes, imsize=32, n_colors=3, n_timewin=7):
    """
    Builds the complete network with 1D-conv layer to integrate time from sequences of EEG images.

    :param input_vars: list of EEG images (one image per time window)
    :param nb_classes: number of classes
    :param imsize: size of the input image (assumes a square input)
    :param n_colors: number of color channels in the image
    :param n_timewin: number of time windows in the snippet
    :return: a pointer to the output of last layer
    """
    convnets = []
    w_init = None
    # Build 7 parallel CNNs with shared weights
    for i in range(n_timewin):
        if i == 0:
            convnet, w_init = build_cnn(input_vars[i], imsize=imsize, n_colors=n_colors)
        else:
            convnet, _ = build_cnn(input_vars[i], w_init=w_init, imsize=imsize, n_colors=n_colors)
        convnets.append(FlattenLayer(convnet))
    # at this point convnets shape is [numTimeWin][n_samples, features]
    # we want the shape to be [n_samples, features, numTimeWin]
    convpool = ConcatLayer(convnets)
    convpool = ReshapeLayer(convpool, ([0], n_timewin, get_output_shape(convnets[0])[1]))
    convpool = DimshuffleLayer(convpool, (0, 2, 1))
    # input to 1D convlayer should be in (batch_size, num_input_channels, input_length)
    convpool = Conv1DLayer(convpool, 64, 3)
    # A fully-connected layer of 512 units with 50% dropout on its inputs:
    convpool = DenseLayer(lasagne.layers.dropout(convpool, p=.5),
            num_units=512, nonlinearity=lasagne.nonlinearities.rectify)
    # And, finally, the output layer with 50% dropout on its inputs:
    convpool = DenseLayer(lasagne.layers.dropout(convpool, p=.5),
            num_units=nb_classes, nonlinearity=lasagne.nonlinearities.softmax)
    return convpool 

def build_convpool_lstm(input_vars, nb_classes, grad_clip=110, imsize=32, n_colors=3, n_timewin=7):
    """
    Builds the complete network with LSTM layer to integrate time from sequences of EEG images.

    :param input_vars: list of EEG images (one image per time window)
    :param nb_classes: number of classes
    :param grad_clip:  the gradient messages are clipped to the given value during
                        the backward pass.
    :param imsize: size of the input image (assumes a square input)
    :param n_colors: number of color channels in the image
    :param n_timewin: number of time windows in the snippet
    :return: a pointer to the output of last layer
    """
    convnets = []
    w_init = None
    # Build 7 parallel CNNs with shared weights
    for i in range(n_timewin):
        if i == 0:
            convnet, w_init = build_cnn(input_vars[i], imsize=imsize, n_colors=n_colors)
        else:
            convnet, _ = build_cnn(input_vars[i], w_init=w_init, imsize=imsize, n_colors=n_colors)
        convnets.append(FlattenLayer(convnet))
    # at this point convnets shape is [numTimeWin][n_samples, features]
    # we want the shape to be [n_samples, features, numTimeWin]
    convpool = ConcatLayer(convnets)
    convpool = ReshapeLayer(convpool, ([0], n_timewin, get_output_shape(convnets[0])[1]))
    # Input to LSTM should have the shape as (batch size, SEQ_LENGTH, num_features)
    convpool = LSTMLayer(convpool, num_units=128, grad_clipping=grad_clip,
        nonlinearity=lasagne.nonlinearities.tanh)
    # We only need the final prediction, we isolate that quantity and feed it
    # to the next layer.
    convpool = SliceLayer(convpool, -1, 1)      # Selecting the last prediction
    # A fully-connected layer of 256 units with 50% dropout on its inputs:
    convpool = DenseLayer(lasagne.layers.dropout(convpool, p=.5),
            num_units=256, nonlinearity=lasagne.nonlinearities.rectify)
    # And, finally, the output layer with 50% dropout on its inputs:
    convpool = DenseLayer(lasagne.layers.dropout(convpool, p=.5),
            num_units=nb_classes, nonlinearity=lasagne.nonlinearities.softmax)
    return convpool 

def mask_loss(loss, mask):
    return loss * lo(LL.FlattenLayer(mask, 1)) 

def build_model():
    net = {}
    net['input'] = InputLayer((None, 3, 32, 32))
    net['conv1'] = ConvLayer(net['input'],
                             num_filters=192,
                             filter_size=5,
                             pad=2,
                             flip_filters=False)
    net['cccp1'] = ConvLayer(
        net['conv1'], num_filters=160, filter_size=1, flip_filters=False)
    net['cccp2'] = ConvLayer(
        net['cccp1'], num_filters=96, filter_size=1, flip_filters=False)
    net['pool1'] = PoolLayer(net['cccp2'],
                             pool_size=3,
                             stride=2,
                             mode='max',
                             ignore_border=False)
    net['drop3'] = DropoutLayer(net['pool1'], p=0.5)
    net['conv2'] = ConvLayer(net['drop3'],
                             num_filters=192,
                             filter_size=5,
                             pad=2,
                             flip_filters=False)
    net['cccp3'] = ConvLayer(
        net['conv2'], num_filters=192, filter_size=1, flip_filters=False)
    net['cccp4'] = ConvLayer(
        net['cccp3'], num_filters=192, filter_size=1, flip_filters=False)
    net['pool2'] = PoolLayer(net['cccp4'],
                             pool_size=3,
                             stride=2,
                             mode='average_exc_pad',
                             ignore_border=False)
    net['drop6'] = DropoutLayer(net['pool2'], p=0.5)
    net['conv3'] = ConvLayer(net['drop6'],
                             num_filters=192,
                             filter_size=3,
                             pad=1,
                             flip_filters=False)
    net['cccp5'] = ConvLayer(
        net['conv3'], num_filters=192, filter_size=1, flip_filters=False)
    net['cccp6'] = ConvLayer(
        net['cccp5'], num_filters=10, filter_size=1, flip_filters=False)
    net['pool3'] = PoolLayer(net['cccp6'],
                             pool_size=8,
                             mode='average_exc_pad',
                             ignore_border=False)
    net['output'] = FlattenLayer(net['pool3'])

    return net 

def build_convpool_mix(input_vars, nb_classes, grad_clip=110, imsize=32, n_colors=3, n_timewin=7):
    """
    Builds the complete network with LSTM and 1D-conv layers combined

    :param input_vars: list of EEG images (one image per time window)
    :param nb_classes: number of classes
    :param grad_clip:  the gradient messages are clipped to the given value during
                        the backward pass.
    :param imsize: size of the input image (assumes a square input)
    :param n_colors: number of color channels in the image
    :param n_timewin: number of time windows in the snippet
    :return: a pointer to the output of last layer
    """
    convnets = []
    w_init = None
    # Build 7 parallel CNNs with shared weights
    for i in range(n_timewin):
        if i == 0:
            convnet, w_init = build_cnn(input_vars[i], imsize=imsize, n_colors=n_colors)
        else:
            convnet, _ = build_cnn(input_vars[i], w_init=w_init, imsize=imsize, n_colors=n_colors)
        convnets.append(FlattenLayer(convnet))
    # at this point convnets shape is [numTimeWin][n_samples, features]
    # we want the shape to be [n_samples, features, numTimeWin]
    convpool = ConcatLayer(convnets)
    convpool = ReshapeLayer(convpool, ([0], n_timewin, get_output_shape(convnets[0])[1]))
    reformConvpool = DimshuffleLayer(convpool, (0, 2, 1))
    # input to 1D convlayer should be in (batch_size, num_input_channels, input_length)
    conv_out = Conv1DLayer(reformConvpool, 64, 3)
    conv_out = FlattenLayer(conv_out)
    # Input to LSTM should have the shape as (batch size, SEQ_LENGTH, num_features)
    lstm = LSTMLayer(convpool, num_units=128, grad_clipping=grad_clip,
        nonlinearity=lasagne.nonlinearities.tanh)
    lstm_out = SliceLayer(lstm, -1, 1)
    # Merge 1D-Conv and LSTM outputs
    dense_input = ConcatLayer([conv_out, lstm_out])
    # A fully-connected layer of 256 units with 50% dropout on its inputs:
    convpool = DenseLayer(lasagne.layers.dropout(dense_input, p=.5),
            num_units=512, nonlinearity=lasagne.nonlinearities.rectify)
    # And, finally, the 10-unit output layer with 50% dropout on its inputs:
    convpool = DenseLayer(convpool,
            num_units=nb_classes, nonlinearity=lasagne.nonlinearities.softmax)
    return convpool 

def network(self):
        if self._network is not None:
            return self._network

        # Build the computational graph using a dummy input.
        import lasagne
        from lasagne.layers.dnn import Conv2DDNNLayer as ConvLayer
        from lasagne.layers import ElemwiseSumLayer, NonlinearityLayer, InputLayer, FlattenLayer, DenseLayer
        from lasagne.layers import batch_norm
        from lasagne.nonlinearities import rectify

        self._network_in = InputLayer(shape=(None, self.nb_channels,) + self.image_shape, input_var=None)
        network_out = []

        if self.convnet_blueprint is not None:
            convnet_layers = [self._network_in]
            layer_blueprints = list(map(str.strip, self.convnet_blueprint.split("->")))
            for i, layer_blueprint in enumerate(layer_blueprints, start=1):
                # eg. "64@3x3(valid) -> 64@3x3(full)"
                nb_filters, rest = layer_blueprint.split("@")
                filter_shape, rest = rest.split("(")
                nb_filters = int(nb_filters)
                filter_shape = tuple(map(int, filter_shape.split("x")))
                pad = rest[:-1]

                preact = ConvLayer(convnet_layers[-1], num_filters=nb_filters, filter_size=filter_shape, stride=(1, 1),
                                   nonlinearity=None, pad=pad, W=lasagne.init.HeNormal(gain='relu'),
                                   name="layer_{}_conv".format(i))

                if self.use_batch_norm:
                    preact = batch_norm(preact)

                layer = NonlinearityLayer(preact, nonlinearity=rectify)
                convnet_layers.append(layer)

            network_out.append(FlattenLayer(preact))

        if self.fullnet_blueprint is not None:
            fullnet_layers = [FlattenLayer(self._network_in)]
            layer_blueprints = list(map(str.strip, self.fullnet_blueprint.split("->")))
            for i, layer_blueprint in enumerate(layer_blueprints, start=1):
                # e.g. "500 -> 500 -> 784"
                hidden_size = int(layer_blueprint)

                preact = DenseLayer(fullnet_layers[-1], num_units=hidden_size,
                                    nonlinearity=None, W=lasagne.init.HeNormal(gain='relu'),
                                    name="layer_{}_dense".format(i))

                if self.use_batch_norm:
                    preact = batch_norm(preact)

                layer = NonlinearityLayer(preact, nonlinearity=rectify)
                fullnet_layers.append(layer)

            network_out.append(preact)

        self._network = ElemwiseSumLayer(network_out)
        # TODO: sigmoid should be applied here instead of within loss function.
        print("Nb. of parameters in model: {}".format(lasagne.layers.count_params(self._network, trainable=True)))
        return self._network 

def network(self):
        if self._network is not None:
            return self._network

        # Build the computational graph using a dummy input.
        import lasagne
        from lasagne.layers.dnn import Conv2DDNNLayer as ConvLayer
        from lasagne.layers import ElemwiseSumLayer, NonlinearityLayer, ExpressionLayer, PadLayer, InputLayer, FlattenLayer, SliceLayer
        # from lasagne.layers import batch_norm
        from lasagne.nonlinearities import rectify

        self._network_in = InputLayer(shape=(None, self.nb_channels,) + self.image_shape, input_var=None)

        convnet_layers = [self._network_in]
        convnet_layers_preact = [self._network_in]
        layer_blueprints = list(map(str.strip, self.convnet_blueprint.split("->")))
        for i, layer_blueprint in enumerate(layer_blueprints, start=1):
            "64@3x3(valid) -> 64@3x3(full)"
            nb_filters, rest = layer_blueprint.split("@")
            filter_shape, rest = rest.split("(")
            nb_filters = int(nb_filters)
            filter_shape = tuple(map(int, filter_shape.split("x")))
            pad = rest[:-1]

            preact = ConvLayer(convnet_layers[-1], num_filters=nb_filters, filter_size=filter_shape, stride=(1, 1), nonlinearity=None, pad=pad, W=lasagne.init.HeNormal(gain='relu'))

            if i > len(layer_blueprints) // 2 and i != len(layer_blueprints):
                shortcut = convnet_layers_preact[len(layer_blueprints)-i]
                if i == len(layer_blueprints):
                    if preact.output_shape[1] != shortcut.output_shape[1]:
                        shortcut = SliceLayer(shortcut, slice(0, 1), axis=1)
                    else:
                        raise NameError("Something is wrong.")

                print("Shortcut from {} to {}".format(len(layer_blueprints)-i, i))
                preact = ElemwiseSumLayer([preact, shortcut])

            convnet_layers_preact.append(preact)

            layer = NonlinearityLayer(preact, nonlinearity=rectify)
            convnet_layers.append(layer)

        self._network = FlattenLayer(preact)
        # network = DenseLayer(l, num_units=int(np.prod(self.image_shape)),
        #                      W=lasagne.init.HeNormal(),
        #                      nonlinearity=None)

        print("Nb. of parameters in model: {}".format(lasagne.layers.count_params(self._network, trainable=True)))
        return self._network