Python keras.applications.mobilenet.relu6() Examples

def conv_block(inputs, filters, weight_decay, name, kernel=(3, 3), strides=(1, 1)):
    '''
    Normal convolution block performs conv+bn+relu6 operations.
    :param inputs: Input Keras tensor in (B, H, W, C_in)
    :param filters: number of filters in the convolution layer
    :param name: name for the convolutional layer
    :param kernel: kernel size
    :param strides: strides for convolution
    :return: Output tensor in (B, H_new, W_new, filters)
    '''
    channel_axis = 1 if K.image_data_format() == 'channels_first' else -1
    x = Conv2D(filters, kernel,
               padding='same',
               use_bias=False,
               kernel_regularizer=l2(weight_decay),
               strides=strides,
               name=name)(inputs)
    x = BatchNormalization(axis=channel_axis, epsilon=1e-5,momentum=0.9,name=name+'_bn')(x)
    return Relu6(x, name=name+'_relu') 

def _conv_block(inputs, filters, kernel, strides):
    """Convolution Block
    This function defines a 2D convolution operation with BN and relu6.

    # Arguments
        inputs: Tensor, input tensor of conv layer.
        filters: Integer, the dimensionality of the output space.
        kernel: An integer or tuple/list of 2 integers, specifying the
            width and height of the 2D convolution window.
        strides: An integer or tuple/list of 2 integers,
            specifying the strides of the convolution along the width
            and height.Can be a single integer to specify the same
            value for all spatial dimensions.

    # Returns
        Output tensor.
    """

    channel_axis = 1 if K.image_data_format() == 'channels_first' else -1

    x = Conv2D(filters, kernel, padding='same', strides=strides)(inputs)
    x = BatchNormalization(axis=channel_axis)(x)
    return Activation(relu6)(x) 

def __init__(self, model):
        super(Keras2Parser, self).__init__()

        # load model files into Keras graph
        if isinstance(model, _string_types):
            try:
                # Keras 2.1.6
                from keras.applications.mobilenet import relu6
                from keras.applications.mobilenet import DepthwiseConv2D
                model = _keras.models.load_model(
                    model,
                    custom_objects={
                        'relu6': _keras.applications.mobilenet.relu6,
                        'DepthwiseConv2D': _keras.applications.mobilenet.DepthwiseConv2D
                    }
                )
            except:
                # Keras. 2.2.2
                import keras.layers as layers
                model = _keras.models.load_model(
                    model,
                    custom_objects={
                        'relu6': layers.ReLU(6, name='relu6'),
                        'DepthwiseConv2D': layers.DepthwiseConv2D
                    }
                )
            self.weight_loaded = True

        elif isinstance(model, tuple):
            model = self._load_model(model[0], model[1])

        else:
            assert False

        # _keras.utils.plot_model(model, "model.png", show_shapes = True)

        # Build network graph
        self.data_format = _keras.backend.image_data_format()
        self.keras_graph = Keras2Graph(model)
        self.keras_graph.build()
        self.lambda_layer_count = 0 

def Relu6(x, **kwargs):
    return Activation(relu6, **kwargs)(x) 

def _bottleneck(inputs, filters, kernel, t, s, r=False):
    """Bottleneck
    This function defines a basic bottleneck structure.

    # Arguments
        inputs: Tensor, input tensor of conv layer.
        filters: Integer, the dimensionality of the output space.
        kernel: An integer or tuple/list of 2 integers, specifying the
            width and height of the 2D convolution window.
        t: Integer, expansion factor.
            t is always applied to the input size.
        s: An integer or tuple/list of 2 integers,specifying the strides
            of the convolution along the width and height.Can be a single
            integer to specify the same value for all spatial dimensions.
        r: Boolean, Whether to use the residuals.

    # Returns
        Output tensor.
    """

    channel_axis = 1 if K.image_data_format() == 'channels_first' else -1
    tchannel = K.int_shape(inputs)[channel_axis] * t

    x = _conv_block(inputs, tchannel, (1, 1), (1, 1))

    x = DepthwiseConv2D(kernel, strides=(s, s),
                        depth_multiplier=1, padding='same')(x)
    x = BatchNormalization(axis=channel_axis)(x)
    x = Activation(relu6)(x)

    x = Conv2D(filters, (1, 1), strides=(1, 1), padding='same')(x)
    x = BatchNormalization(axis=channel_axis)(x)

    if r:
        x = add([x, inputs])
    return x 

def _load_model(self, model_network_path, model_weight_path):
        """Load a keras model from disk

        Parameters
        ----------
        model_network_path: str
            Path where the model network path is (json file)

        model_weight_path: str
            Path where the model network weights are (hd5 file)

        Returns
        -------
        model: A keras model
        """
        from keras.models import model_from_json

        # Load the model network
        json_file = open(model_network_path, 'r')
        loaded_model_json = json_file.read()
        json_file.close()

        # Load the model weights

        try:
            from keras.applications.mobilenet import relu6
            from keras.applications.mobilenet import DepthwiseConv2D
            loaded_model = model_from_json(loaded_model_json, custom_objects={
                'relu6': _keras.applications.mobilenet.relu6,
                'DepthwiseConv2D': _keras.applications.mobilenet.DepthwiseConv2D})
        except:
            import keras.layers as layers
            loaded_model = model_from_json(loaded_model_json, custom_objects={
                'relu6': layers.ReLU(6, name='relu6'),
                'DepthwiseConv2D': layers.DepthwiseConv2D})


        if model_weight_path:
            if os.path.isfile(model_weight_path):
                loaded_model.load_weights(model_weight_path)
                self.weight_loaded = True
                print("Network file [{}] and [{}] is loaded successfully.".format(model_network_path, model_weight_path))

            else:
                print("Warning: Weights File [%s] is not found." % (model_weight_path))

        return loaded_model 

def _get_activation_name_from_keras_layer(keras_layer):
    if isinstance(keras_layer, _keras.layers.advanced_activations.LeakyReLU):
        non_linearity = "LEAKYRELU"
    elif isinstance(keras_layer, _keras.layers.advanced_activations.PReLU):
        non_linearity = "PRELU"
    elif isinstance(keras_layer, _keras.layers.advanced_activations.ELU):
        non_linearity = "ELU"
    elif isinstance(keras_layer, _keras.layers.advanced_activations.ThresholdedReLU):
        non_linearity = "THRESHOLDEDRELU"
    elif isinstance(keras_layer, _keras.layers.advanced_activations.Softmax):
        non_linearity = "SOFTMAX"
    else:
        import six

        if six.PY2:
            act_name = keras_layer.activation.func_name
        else:
            act_name = keras_layer.activation.__name__

        if act_name == "softmax":
            non_linearity = "SOFTMAX"
        elif act_name == "sigmoid":
            non_linearity = "SIGMOID"
        elif act_name == "tanh":
            non_linearity = "TANH"
        elif act_name == "relu":
            non_linearity = "RELU"
        elif act_name == "relu6":
            non_linearity = "RELU6"
        elif act_name == "softplus":
            non_linearity = "SOFTPLUS"
        elif act_name == "softsign":
            non_linearity = "SOFTSIGN"
        elif act_name == "hard_sigmoid":
            non_linearity = "SIGMOID_HARD"
        elif act_name == "elu":
            non_linearity = "UNIT_ELU"
        elif act_name == "linear":
            non_linearity = "LINEAR"
        elif act_name == "selu":
            non_linearity = "SELU"
        else:
            non_linearity = "CUSTOM"

    return non_linearity 

def test_tiny_mobilenet_arch(self, model_precision=_MLMODEL_FULL_PRECISION):
        def ReLU6(x, name):
            if keras.__version__ >= _StrictVersion("2.2.1"):
                return ReLU(6.0, name=name)(x)
            else:
                return Activation(relu6, name=name)(x)

        img_input = Input(shape=(32, 32, 3))
        x = Conv2D(
            4, (3, 3), padding="same", use_bias=False, strides=(2, 2), name="conv1"
        )(img_input)
        x = BatchNormalization(axis=-1, name="conv1_bn")(x)
        x = ReLU6(x, name="conv1_relu")

        x = DepthwiseConv2D(
            (3, 3),
            padding="same",
            depth_multiplier=1,
            strides=(1, 1),
            use_bias=False,
            name="conv_dw_1",
        )(x)
        x = BatchNormalization(axis=-1, name="conv_dw_1_bn")(x)
        x = ReLU6(x, name="conv_dw_1_relu")

        x = Conv2D(
            8, (1, 1), padding="same", use_bias=False, strides=(1, 1), name="conv_pw_1"
        )(x)
        x = BatchNormalization(axis=-1, name="conv_pw_1_bn")(x)
        x = ReLU6(x, name="conv_pw_1_relu")

        x = DepthwiseConv2D(
            (3, 3),
            padding="same",
            depth_multiplier=1,
            strides=(2, 2),
            use_bias=False,
            name="conv_dw_2",
        )(x)
        x = BatchNormalization(axis=-1, name="conv_dw_2_bn")(x)
        x = ReLU6(x, name="conv_dw_2_relu")

        x = Conv2D(
            8, (1, 1), padding="same", use_bias=False, strides=(2, 2), name="conv_pw_2"
        )(x)
        x = BatchNormalization(axis=-1, name="conv_pw_2_bn")(x)
        x = ReLU6(x, name="conv_pw_2_relu")

        model = Model(inputs=[img_input], outputs=[x])

        self._test_model(model, delta=1e-2, model_precision=model_precision)