Python keras.backend.normalize_data_format() Examples

def __init__(self, upsampling=(2, 2), output_size=None, data_format=None, **kwargs):

        super(BilinearUpsampling, self).__init__(**kwargs)

        self.data_format = K.normalize_data_format(data_format)
        self.input_spec = InputSpec(ndim=4)
        if output_size:
            self.output_size = conv_utils.normalize_tuple(
                output_size, 2, 'output_size')
            self.upsampling = None
        else:
            self.output_size = None
            self.upsampling = conv_utils.normalize_tuple(
                upsampling, 2, 'upsampling') 

def __init__(self, padding=1, data_format=None, **kwargs):
        super(ChannelPadding, self).__init__(**kwargs)
        self.padding = conv_utils.normalize_tuple(padding, 2, 'padding')
        self.data_format = normalize_data_format(data_format)
        self.input_spec = InputSpec(ndim=4) 

def __init__(self, scale_factor=2, data_format=None, **kwargs):
        super(SubPixelUpscaling, self).__init__(**kwargs)

        self.scale_factor = scale_factor
        self.data_format = normalize_data_format(data_format) 

def __init__(self, upsampling=(2, 2), output_size=None, data_format=None, **kwargs):

        super(BilinearUpsampling, self).__init__(**kwargs)

        self.data_format = K.normalize_data_format(data_format)
        self.input_spec = InputSpec(ndim=4)
        if output_size:
            self.output_size = conv_utils.normalize_tuple(
                output_size, 2, 'output_size')
            self.upsampling = None
        else:
            self.output_size = None
            self.upsampling = conv_utils.normalize_tuple(
                upsampling, 2, 'upsampling') 

def normalize_data_format(value):
    """Checks that the value correspond to a valid data format.

    Copy of the function in keras-team/keras because it's not public API.

    # Arguments
        value: String or None. `'channels_first'` or `'channels_last'`.

    # Returns
        A string, either `'channels_first'` or `'channels_last'`

    # Example
    ```python
        >>> from keras import backend as K
        >>> K.normalize_data_format(None)
        'channels_first'
        >>> K.normalize_data_format('channels_last')
        'channels_last'
    ```

    # Raises
        ValueError: if `value` or the global `data_format` invalid.
    """
    if value is None:
        value = K.image_data_format()
    data_format = value.lower()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('The `data_format` argument must be one of '
                         '"channels_first", "channels_last". Received: ' +
                         str(value))
    return data_format 

def __init__(self, scale_factor=2, data_format=None, **kwargs):
        super(SubPixelUpscaling, self).__init__(**kwargs)

        self.scale_factor = scale_factor
        self.data_format = normalize_data_format(data_format) 

def __init__(self, loss_function, lats, data_format='channels_last', weighting='cosine'):
        """
        Initialize a weighted loss.

        :param loss_function: method: Keras loss function to apply after the weighting
        :param lats: ndarray: 1-dimensional array of latitude coordinates
        :param data_format: Keras data_format ('channels_first' or 'channels_last')
        :param weighting: str: type of weighting to apply. Options are:
            cosine: weight by the cosine of the latitude (default)
            midlatitude: weight by the cosine of the latitude but also apply a 25% reduction to the equator and boost
                to the mid-latitudes
        """
        self.loss_function = loss_function
        self.lats = lats
        self.data_format = K.normalize_data_format(data_format)
        if weighting not in ['cosine', 'midlatitude']:
            raise ValueError("'weighting' must be one of 'cosine' or 'midlatitude'")
        self.weighting = weighting
        lat_tensor = K.zeros(lats.shape)
        print(lats)
        lat_tensor.assign(K.cast_to_floatx(lats[:]))
        self.weights = K.cos(lat_tensor * np.pi / 180.)
        if self.weighting == 'midlatitude':
            self.weights = self.weights - 0.25 * K.sin(lat_tensor * 2 * np.pi / 180.)
        self.is_init = False

        self.__name__ = 'latitude_weighted_loss' 

def __init__(self, size=(2, 2), data_format=None, **kwargs):
        super().__init__(**kwargs)
        self.data_format = K.normalize_data_format(data_format)
        self.size = conv_utils.normalize_tuple(size, 2, "size") 

def __init__(self, scale_factor=2, data_format=None, **kwargs):
        super(SubPixelUpscaling, self).__init__(**kwargs)

        self.scale_factor = scale_factor
        self.data_format = K.normalize_data_format(data_format) 

def __init__(self, ch_j, n_j,
                 kernel_size=(3, 3),
                 strides=(1, 1),
                 r_num=1,
                 b_alphas=[8, 8, 8],
                 padding='same',
                 data_format='channels_last',
                 dilation_rate=(1, 1),
                 kernel_initializer='glorot_uniform',
                 bias_initializer='zeros',
                 kernel_regularizer=None,
                 activity_regularizer=None,
                 kernel_constraint=None,
                 **kwargs):
        super(Conv2DCaps, self).__init__(**kwargs)
        rank = 2
        self.ch_j = ch_j  # Number of capsules in layer J
        self.n_j = n_j  # Number of neurons in a capsule in J
        self.kernel_size = conv_utils.normalize_tuple(kernel_size, rank, 'kernel_size')
        self.strides = conv_utils.normalize_tuple(strides, rank, 'strides')
        self.r_num = r_num
        self.b_alphas = b_alphas
        self.padding = conv_utils.normalize_padding(padding)
        #self.data_format = conv_utils.normalize_data_format(data_format)
        self.data_format = K.normalize_data_format(data_format)
        self.dilation_rate = (1, 1)
        self.kernel_initializer = initializers.get(kernel_initializer)
        self.bias_initializer = initializers.get(bias_initializer)
        self.kernel_regularizer = regularizers.get(kernel_regularizer)
        self.activity_regularizer = regularizers.get(activity_regularizer)
        self.kernel_constraint = constraints.get(kernel_constraint)
        self.input_spec = InputSpec(ndim=rank + 3) 

def __init__(self, rank,
                 filters,
                 kernel_size,
                 strides=1,
                 padding='valid',
                 data_format='channels_last',
                 dilation_rate=1,
                 activation=None,
                 use_bias=True,
                 normalize_weight=False,
                 kernel_initializer='quaternion',
                 bias_initializer='zeros',
                 gamma_diag_initializer=sqrt_init,
                 gamma_off_initializer='zeros',
                 kernel_regularizer=None,
                 bias_regularizer=None,
                 gamma_diag_regularizer=None,
                 gamma_off_regularizer=None,
                 activity_regularizer=None,
                 kernel_constraint=None,
                 bias_constraint=None,
                 gamma_diag_constraint=None,
                 gamma_off_constraint=None,
                 init_criterion='he',
                 seed=None,
                 spectral_parametrization=False,
                 epsilon=1e-7,
                 **kwargs):
        super(QuaternionConv, self).__init__(**kwargs)
        self.rank = rank
        self.filters = filters
        self.kernel_size = conv_utils.normalize_tuple(kernel_size, rank, 'kernel_size')
        self.strides = conv_utils.normalize_tuple(strides, rank, 'strides')
        self.padding = conv_utils.normalize_padding(padding)
        self.data_format = K.normalize_data_format(data_format)
        self.dilation_rate = conv_utils.normalize_tuple(dilation_rate, rank, 'dilation_rate')
        self.activation = activations.get(activation)
        self.use_bias = use_bias
        self.normalize_weight = normalize_weight
        self.init_criterion = init_criterion
        self.spectral_parametrization = spectral_parametrization
        self.epsilon = epsilon
        self.kernel_initializer = sanitizedInitGet(kernel_initializer)
        self.bias_initializer = sanitizedInitGet(bias_initializer)
        self.gamma_diag_initializer = sanitizedInitGet(gamma_diag_initializer)
        self.gamma_off_initializer = sanitizedInitGet(gamma_off_initializer)
        self.kernel_regularizer = regularizers.get(kernel_regularizer)
        self.bias_regularizer = regularizers.get(bias_regularizer)
        self.gamma_diag_regularizer = regularizers.get(gamma_diag_regularizer)
        self.gamma_off_regularizer = regularizers.get(gamma_off_regularizer)
        self.activity_regularizer = regularizers.get(activity_regularizer)
        self.kernel_constraint = constraints.get(kernel_constraint)
        self.bias_constraint = constraints.get(bias_constraint)
        self.gamma_diag_constraint = constraints.get(gamma_diag_constraint)
        self.gamma_off_constraint = constraints.get(gamma_off_constraint)
        if seed is None:
            self.seed = np.random.randint(1, 10e6)
        else:
            self.seed = seed
        self.input_spec = InputSpec(ndim=self.rank + 2) 

def row_conv2d(inputs, kernel, kernel_size, strides, output_shape, data_format=None):
    """Apply 2D conv with weights shared only along rows.

    Adapted from K.local_conv2d by @jweyn

    # Arguments
        inputs: 4D tensor with shape:
                (batch_size, filters, new_rows, new_cols)
                if data_format='channels_first'
                or 4D tensor with shape:
                (batch_size, new_rows, new_cols, filters)
                if data_format='channels_last'.
        kernel: the row-shared weights for convolution,
                with shape (output_rows, kernel_size, input_channels, filters)
        kernel_size: a tuple of 2 integers, specifying the
                     width and height of the 2D convolution window.
        strides: a tuple of 2 integers, specifying the strides
                 of the convolution along the width and height.
        output_shape: a tuple with (output_row, output_col)
        data_format: the data format, channels_first or channels_last

    # Returns
        A 4d tensor with shape:
        (batch_size, filters, new_rows, new_cols)
        if data_format='channels_first'
        or 4D tensor with shape:
        (batch_size, new_rows, new_cols, filters)
        if data_format='channels_last'.

    # Raises
        ValueError: if `data_format` is neither
                    `channels_last` or `channels_first`.
    """
    data_format = K.normalize_data_format(data_format)

    stride_row, stride_col = strides
    output_row, output_col = output_shape

    out = []
    for i in range(output_row):
        # Slice the rows with the neighbors they need
        slice_row = slice(i * stride_row, i * stride_col + kernel_size[0])
        if data_format == 'channels_first':
            x = inputs[:, :, slice_row, :]  # batch, 16, 5, 144
        else:
            x = inputs[:, slice_row, :, :]  # batch, 5, 144, 16
        # Convolve, resulting in an array with only one row: batch, 1, 140, 6 or batch, 6, 1, 140
        x = K.conv2d(x, kernel[i], strides=strides, padding='valid', data_format=data_format)
        out.append(x)

    if data_format == 'channels_first':
        output = K.concatenate(out, axis=2)
    else:
        output = K.concatenate(out, axis=1)
    del x
    del out
    return output