Python backend.image_data_format方法代码示例

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def call(self, x):
        power_spectrogram = super(Melspectrogram, self).call(x)
        # now,  channels_first: (batch_sample, n_ch, n_freq, n_time)
        #       channels_last: (batch_sample, n_freq, n_time, n_ch)
        if self.image_data_format == 'channels_first':
            power_spectrogram = K.permute_dimensions(power_spectrogram, [0, 1, 3, 2])
        else:
            power_spectrogram = K.permute_dimensions(power_spectrogram, [0, 3, 2, 1])
        # now, whatever image_data_format, (batch_sample, n_ch, n_time, n_freq)
        output = K.dot(power_spectrogram, self.freq2mel)
        if self.image_data_format == 'channels_first':
            output = K.permute_dimensions(output, [0, 1, 3, 2])
        else:
            output = K.permute_dimensions(output, [0, 3, 2, 1])
        if self.power_melgram != 2.0:
            output = K.pow(K.sqrt(output), self.power_melgram)
        if self.return_decibel_melgram:
            output = backend_keras.amplitude_to_decibel(output)
        return output 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def __init__(
        self, win_length: int = 5, mode: str = 'symmetric', data_format: str = 'default', **kwargs
    ):

        assert data_format in ('default', 'channels_first', 'channels_last')
        assert win_length >= 3
        assert mode.lower() in ('symmetric', 'reflect', 'constant')

        if data_format == 'default':
            self.data_format = K.image_data_format()
        else:
            self.data_format = data_format

        self.win_length = win_length
        self.mode = mode
        super(Delta, self).__init__(**kwargs) 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def conv2d_bn(x,
              filters,
              kernel_size,
              strides=1,
              padding='same',
              activation='relu',
              use_bias=False,
              name=None):
    x = Conv2D(filters,
               kernel_size,
               strides=strides,
               padding=padding,
               use_bias=use_bias,
               name=name)(x)
    if not use_bias:
        bn_axis = 1 if K.image_data_format() == 'channels_first' else 3
        bn_name = _generate_layer_name('BatchNorm', prefix=name)
        x = BatchNormalization(axis=bn_axis, momentum=0.995, epsilon=0.001,
                               scale=False, name=bn_name)(x)
    if activation is not None:
        ac_name = _generate_layer_name('Activation', prefix=name)
        x = Activation(activation, name=ac_name)(x)
    return x 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def __initial_conv_block_inception(input_tensor, weight_decay=5e-4):
    """ Adds an initial conv block, with batch norm and relu for the inception resnext
    Args:
        input_tensor: input Keras tensor
        weight_decay: weight decay factor
    Returns: a Keras tensor
    """
    channel_axis = 1 if K.image_data_format() == 'channels_first' else -1

    x = Conv2D(64, (7, 7), padding='same', use_bias=False, kernel_initializer='he_normal',
               kernel_regularizer=l2(weight_decay), strides=(2, 2))(input_tensor)
    x = BatchNormalization(axis=channel_axis)(x)
    x = LeakyReLU()(x)

    x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)

    return x 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def __init__(self, rank,
                 use_radius=False,
                 data_format=None,
                 **kwargs):
        super(_CoordinateChannel, self).__init__(**kwargs)

        if data_format not in [None, 'channels_first', 'channels_last']:
            raise ValueError('`data_format` must be either "channels_last", "channels_first" '
                             'or None.')

        self.rank = rank
        self.use_radius = use_radius
        self.data_format = K.image_data_format() if data_format is None else data_format
        self.axis = 1 if K.image_data_format() == 'channels_first' else -1

        self.input_spec = InputSpec(min_ndim=2)
        self.supports_masking = True 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def correct_pad(backend, inputs, kernel_size):
    """Returns a tuple for zero-padding for 2D convolution with downsampling.

    # Arguments
        input_size: An integer or tuple/list of 2 integers.
        kernel_size: An integer or tuple/list of 2 integers.

    # Returns
        A tuple.
    """
    img_dim = 2 if backend.image_data_format() == 'channels_first' else 1
    input_size = backend.int_shape(inputs)[img_dim:(img_dim + 2)]

    if isinstance(kernel_size, int):
        kernel_size = (kernel_size, kernel_size)

    if input_size[0] is None:
        adjust = (1, 1)
    else:
        adjust = (1 - input_size[0] % 2, 1 - input_size[1] % 2)

    correct = (kernel_size[0] // 2, kernel_size[1] // 2)

    return ((correct[0] - adjust[0], correct[0]),
            (correct[1] - adjust[1], correct[1])) 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def fire_module(x, fire_id, squeeze=16, expand=64):
    s_id = 'fire' + str(fire_id) + '/'

    if K.image_data_format() == 'channels_first':
        channel_axis = 1
    else:
        channel_axis = 3

    x = Conv2D(squeeze, (1, 1), padding='valid', name=s_id + sq1x1)(x)
    x = Activation('relu', name=s_id + relu + sq1x1)(x)

    left = Conv2D(expand, (1, 1), padding='valid', name=s_id + exp1x1)(x)
    left = Activation('relu', name=s_id + relu + exp1x1)(left)

    right = Conv2D(expand, (3, 3), padding='same', name=s_id + exp3x3)(x)
    right = Activation('relu', name=s_id + relu + exp3x3)(right)

    x = concatenate([left, right], axis=channel_axis, name=s_id + 'concat')
    return x


# Original SqueezeNet from paper. 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def correct_pad(backend, inputs, kernel_size):
    """Returns a tuple for zero-padding for 2D convolution with downsampling.
    # Arguments
        input_size: An integer or tuple/list of 2 integers.
        kernel_size: An integer or tuple/list of 2 integers.
    # Returns
        A tuple.
    """
    img_dim = 2 if backend.image_data_format() == 'channels_first' else 1
    input_size = backend.int_shape(inputs)[img_dim:(img_dim + 2)]

    if isinstance(kernel_size, int):
        kernel_size = (kernel_size, kernel_size)

    if input_size[0] is None:
        adjust = (1, 1)
    else:
        adjust = (1 - input_size[0] % 2, 1 - input_size[1] % 2)

    correct = (kernel_size[0] // 2, kernel_size[1] // 2)

    return ((correct[0] - adjust[0], correct[0]),
            (correct[1] - adjust[1], correct[1])) 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def _se_block(inputs, filters, se_ratio, prefix):
    x = GlobalAveragePooling2D(name=prefix + 'squeeze_excite/AvgPool')(inputs)
    if K.image_data_format() == 'channels_first':
        x = Reshape((filters, 1, 1))(x)
    else:
        x = Reshape((1, 1, filters))(x)
    x = Conv2D(_depth(filters * se_ratio),
                      kernel_size=1,
                      padding='same',
                      name=prefix + 'squeeze_excite/Conv')(x)
    x = ReLU(name=prefix + 'squeeze_excite/Relu')(x)
    x = Conv2D(filters,
                      kernel_size=1,
                      padding='same',
                      name=prefix + 'squeeze_excite/Conv_1')(x)
    x = Activation(hard_sigmoid)(x)
    #if K.backend() == 'theano':
        ## For the Theano backend, we have to explicitly make
        ## the excitation weights broadcastable.
        #x = Lambda(
            #lambda br: K.pattern_broadcast(br, [True, True, True, False]),
            #output_shape=lambda input_shape: input_shape,
            #name=prefix + 'squeeze_excite/broadcast')(x)
    x = Multiply(name=prefix + 'squeeze_excite/Mul')([inputs, x])
    return x 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def _conv_block(self, inputs, filters, kernel, strides, nl):
        """Convolution Block
        This function defines a 2D convolution operation with BN and activation.
        # 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.
            nl: String, nonlinearity activation type.
        # 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 self._return_activation(x, nl) 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def _bn_relu_conv_block(input, filters, kernel=(3, 3), stride=(1, 1), weight_decay=5e-4):
    ''' Adds a Batchnorm-Relu-Conv block for DPN
    Args:
        input: input tensor
        filters: number of output filters
        kernel: convolution kernel size
        stride: stride of convolution
    Returns: a keras tensor
    '''
    channel_axis = 1 if K.image_data_format() == 'channels_first' else -1

    x = Conv2D(filters, kernel, padding='same', use_bias=False, kernel_initializer='he_normal',
               kernel_regularizer=l2(weight_decay), strides=stride)(input)
    x = BatchNormalization(axis=channel_axis)(x)
    x = Activation('relu')(x)
    return x 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def __init__(
        self,
        n_dft=512,
        n_hop=None,
        padding='same',
        power_spectrogram=2.0,
        return_decibel_spectrogram=False,
        trainable_kernel=False,
        image_data_format='default',
        **kwargs,
    ):
        assert n_dft > 1 and ((n_dft & (n_dft - 1)) == 0), (
            'n_dft should be > 1 and power of 2, but n_dft == %d' % n_dft
        )
        assert isinstance(trainable_kernel, bool)
        assert isinstance(return_decibel_spectrogram, bool)
        assert padding in ('same', 'valid')
        if n_hop is None:
            n_hop = n_dft // 2

        assert image_data_format in ('default', 'channels_first', 'channels_last')
        if image_data_format == 'default':
            self.image_data_format = K.image_data_format()
        else:
            self.image_data_format = image_data_format

        self.n_dft = n_dft
        assert n_dft % 2 == 0
        self.n_filter = n_dft // 2 + 1
        self.trainable_kernel = trainable_kernel
        self.n_hop = n_hop
        self.padding = padding
        self.power_spectrogram = float(power_spectrogram)
        self.return_decibel_spectrogram = return_decibel_spectrogram
        super(Spectrogram, self).__init__(**kwargs) 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def build(self, input_shape):
        self.n_ch = input_shape[1]
        self.len_src = input_shape[2]
        self.is_mono = self.n_ch == 1
        if self.image_data_format == 'channels_first':
            self.ch_axis_idx = 1
        else:
            self.ch_axis_idx = 3
        if self.len_src is not None:
            assert self.len_src >= self.n_dft, 'Hey! The input is too short!'

        self.n_frame = conv_output_length(self.len_src, self.n_dft, self.padding, self.n_hop)

        dft_real_kernels, dft_imag_kernels = backend.get_stft_kernels(self.n_dft)
        self.dft_real_kernels = K.variable(dft_real_kernels, dtype=K.floatx(), name="real_kernels")
        self.dft_imag_kernels = K.variable(dft_imag_kernels, dtype=K.floatx(), name="imag_kernels")
        # kernels shapes: (filter_length, 1, input_dim, nb_filter)?
        if self.trainable_kernel:
            self.trainable_weights.append(self.dft_real_kernels)
            self.trainable_weights.append(self.dft_imag_kernels)
        else:
            self.non_trainable_weights.append(self.dft_real_kernels)
            self.non_trainable_weights.append(self.dft_imag_kernels)

        super(Spectrogram, self).build(input_shape)
        # self.built = True 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def compute_output_shape(self, input_shape):
        if self.image_data_format == 'channels_first':
            return input_shape[0], self.n_ch, self.n_filter, self.n_frame
        else:
            return input_shape[0], self.n_filter, self.n_frame, self.n_ch 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import image_data_format [as 别名]
def get_config(self):
        config = {
            'n_dft': self.n_dft,
            'n_hop': self.n_hop,
            'padding': self.padding,
            'power_spectrogram': self.power_spectrogram,
            'return_decibel_spectrogram': self.return_decibel_spectrogram,
            'trainable_kernel': self.trainable_kernel,
            'image_data_format': self.image_data_format,
        }
        base_config = super(Spectrogram, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))