Python tensorflow.keras.backend.image_data_format() Examples

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 

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 

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) 

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) 

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 

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 

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 

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])) 

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. 

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])) 

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 

def _bottleneck(self, inputs, filters, kernel, e, s, squeeze, nl):
        """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.
            e: 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.
            squeeze: Boolean, Whether to use the squeeze.
            nl: String, nonlinearity activation type.
        # Returns
            Output tensor.
        """

        channel_axis = 1 if K.image_data_format() == 'channels_first' else -1
        input_shape = K.int_shape(inputs)
        tchannel = input_shape[channel_axis] * e
        r = s == 1 and input_shape[3] == filters

        x = self._conv_block(inputs, tchannel, (1, 1), (1, 1), nl)

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

        if squeeze:
            x = Lambda(lambda x: x * self._squeeze(x))(x)

        x = self._return_activation(x, nl)

        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 shuffle_unit(inputs, out_channels, bottleneck_ratio,strides=2,stage=1,block=1):
    if K.image_data_format() == 'channels_last':
        bn_axis = -1
    else:
        raise ValueError('Only channels last supported')

    prefix = 'stage{}/block{}'.format(stage, block)
    bottleneck_channels = int(out_channels * bottleneck_ratio)
    if strides < 2:
        c_hat, c = channel_split(inputs, '{}/spl'.format(prefix))
        inputs = c

    x = Conv2D(bottleneck_channels, kernel_size=(1,1), strides=1, padding='same', name='{}/1x1conv_1'.format(prefix))(inputs)
    x = BatchNormalization(axis=bn_axis, name='{}/bn_1x1conv_1'.format(prefix))(x)
    x = Activation('relu', name='{}/relu_1x1conv_1'.format(prefix))(x)
    x = DepthwiseConv2D(kernel_size=3, strides=strides, padding='same', name='{}/3x3dwconv'.format(prefix))(x)
    x = BatchNormalization(axis=bn_axis, name='{}/bn_3x3dwconv'.format(prefix))(x)
    x = Conv2D(bottleneck_channels, kernel_size=1,strides=1,padding='same', name='{}/1x1conv_2'.format(prefix))(x)
    x = BatchNormalization(axis=bn_axis, name='{}/bn_1x1conv_2'.format(prefix))(x)
    x = Activation('relu', name='{}/relu_1x1conv_2'.format(prefix))(x)

    if strides < 2:
        ret = Concatenate(axis=bn_axis, name='{}/concat_1'.format(prefix))([x, c_hat])
    else:
        s2 = DepthwiseConv2D(kernel_size=3, strides=2, padding='same', name='{}/3x3dwconv_2'.format(prefix))(inputs)
        s2 = BatchNormalization(axis=bn_axis, name='{}/bn_3x3dwconv_2'.format(prefix))(s2)
        s2 = Conv2D(bottleneck_channels, kernel_size=1,strides=1,padding='same', name='{}/1x1_conv_3'.format(prefix))(s2)
        s2 = BatchNormalization(axis=bn_axis, name='{}/bn_1x1conv_3'.format(prefix))(s2)
        s2 = Activation('relu', name='{}/relu_1x1conv_3'.format(prefix))(s2)
        ret = Concatenate(axis=bn_axis, name='{}/concat_2'.format(prefix))([x, s2])

    ret = Lambda(channel_shuffle, name='{}/channel_shuffle'.format(prefix))(ret)

    return ret 

def _grouped_convolution_block(input, grouped_channels, cardinality, strides, weight_decay=5e-4):
    ''' Adds a grouped convolution block. It is an equivalent block from the paper
    Args:
        input: input tensor
        grouped_channels: grouped number of filters
        cardinality: cardinality factor describing the number of groups
        strides: performs strided convolution for downscaling if > 1
        weight_decay: weight decay term
    Returns: a keras tensor
    '''
    init = input
    channel_axis = 1 if K.image_data_format() == 'channels_first' else -1

    group_list = []

    if cardinality == 1:
        # with cardinality 1, it is a standard convolution
        x = Conv2D(grouped_channels, (3, 3), padding='same', use_bias=False, strides=strides,
                   kernel_initializer='he_normal', kernel_regularizer=l2(weight_decay))(init)
        x = BatchNormalization(axis=channel_axis)(x)
        x = Activation('relu')(x)
        return x

    for c in range(cardinality):
        x = Lambda(lambda z: z[:, :, :, c * grouped_channels:(c + 1) * grouped_channels]
                   if K.image_data_format() == 'channels_last' else
                   lambda z: z[:, c * grouped_channels:(c + 1) * grouped_channels, :, :])(input)

        x = Conv2D(grouped_channels, (3, 3), padding='same', use_bias=False, strides=strides,
                   kernel_initializer='he_normal', kernel_regularizer=l2(weight_decay))(x)

        group_list.append(x)

    group_merge = concatenate(group_list, axis=channel_axis)
    group_merge = BatchNormalization(axis=channel_axis)(group_merge)
    group_merge = Activation('relu')(group_merge)
    return group_merge 

def preprocess_input(x, data_format=None):
    """Preprocesses a tensor encoding a batch of images.
       Obtained from https://github.com/cypw/DPNs

        # Arguments
            x: input Numpy tensor, 4D.
            data_format: data format of the image tensor.

        # Returns
            Preprocessed tensor.
        """
    if data_format is None:
        data_format = K.image_data_format()
    assert data_format in {'channels_last', 'channels_first'}

    if data_format == 'channels_first':
        # 'RGB'->'BGR'
        x = x[:, ::-1, :, :]
        # Zero-center by mean pixel
        x[:, 0, :, :] -= 104
        x[:, 1, :, :] -= 117
        x[:, 2, :, :] -= 128
    else:
        # 'RGB'->'BGR'
        x = x[:, :, :, ::-1]
        # Zero-center by mean pixel
        x[:, :, :, 0] -= 104
        x[:, :, :, 1] -= 117
        x[:, :, :, 2] -= 124

    x *= 0.0167
    return x 

def squeeze_excite_block(input, ratio=16):
    ''' Create a channel-wise squeeze-excite block

    Args:
        input: input tensor
        filters: number of output filters

    Returns: a keras tensor

    References
    -   [Squeeze and Excitation Networks](https://arxiv.org/abs/1709.01507)
    '''
    init = input
    channel_axis = 1 if K.image_data_format() == "channels_first" else -1
    filters = init._keras_shape[channel_axis]
    se_shape = (1, 1, filters)

    se = GlobalAveragePooling2D()(init)
    se = Reshape(se_shape)(se)
    se = Dense(filters // ratio, activation='relu', kernel_initializer='he_normal', use_bias=False)(se)
    se = Dense(filters, activation='sigmoid', kernel_initializer='he_normal', use_bias=False)(se)

    if K.image_data_format() == 'channels_first':
        se = Permute((3, 1, 2))(se)

    x = multiply([init, se])
    return x 

def preprocess_input(x, data_format=None, mode="caffe", **kwargs):
    """Preprocesses a tensor or Numpy array encoding a batch of images.
    # Arguments
        x: Input Numpy or symbolic tensor, 3D or 4D.
            The preprocessed data is written over the input data
            if the data types are compatible. To avoid this
            behaviour, `numpy.copy(x)` can be used.
        data_format: Data format of the image tensor/array.
        mode: One of "caffe", "tf" or "torch".
            - caffe: will convert the images from RGB to BGR,
                then will zero-center each color channel with
                respect to the ImageNet dataset,
                without scaling.
            - tf: will scale pixels between -1 and 1,
                sample-wise.
            - torch: will scale pixels between 0 and 1 and then
                will normalize each channel with respect to the
                ImageNet dataset.
    # Returns
        Preprocessed tensor or Numpy array.
    # Raises
        ValueError: In case of unknown `data_format` argument.
    """

    if data_format is None:
        data_format = backend.image_data_format()
    if data_format not in {"channels_first", "channels_last"}:
        raise ValueError("Unknown data_format " + str(data_format))
    return _preprocess_symbolic_input(x, data_format=data_format, mode=mode, **kwargs) 

def __init__(self, size=96, num_classes=10, depth=64, reduction_ratio=4, num_split=8, num_block=3):
        self.depth = depth # number of channels
        self.ratio = reduction_ratio # ratio of channel reduction in SE module
        self.num_split = num_split # number of splitting trees for ResNeXt (so called cardinality)
        self.num_block = num_block # number of residual blocks
        if K.image_data_format() == 'channels_first':
            self.channel_axis = 1
        else:
            self.channel_axis = 3
        self.model = self.build_model(Input(shape=(size,size,3)), num_classes) 

def depth_to_space(input, scale, data_format=None):
    """ Uses phase shift algorithm to convert
    channels/depth to spatial resolution """
    if data_format is None:
        data_format = K.image_data_format()
    data_format = data_format.lower()
    input = _preprocess_conv2d_input(input, data_format)
    out = tf.nn.depth_to_space(input, scale)
    out = _postprocess_conv2d_output(out, data_format)
    return out 

def channel_squeeze_excite_block(input, ratio=0.25):
    init = input
    channel_axis = 1 if K.image_data_format() == "channels_first" else -1
    filters = init._keras_shape[channel_axis]
    cse_shape = (1, 1, filters)

    cse = layers.GlobalAveragePooling2D()(init)
    cse = layers.Reshape(cse_shape)(cse)
    ratio_filters = int(np.round(filters * ratio))
    if ratio_filters < 1:
        ratio_filters += 1
    cse = layers.Conv2D(
        ratio_filters,
        (1, 1),
        padding="same",
        activation="relu",
        kernel_initializer="he_normal",
        use_bias=False,
    )(cse)
    cse = layers.BatchNormalization()(cse)
    cse = layers.Conv2D(
        filters,
        (1, 1),
        activation="sigmoid",
        kernel_initializer="he_normal",
        use_bias=False,
    )(cse)

    if K.image_data_format() == "channels_first":
        cse = layers.Permute((3, 1, 2))(cse)

    cse = layers.Multiply()([init, cse])
    return cse 

def space_to_depth(input, scale, data_format=None):
    """ Uses phase shift algorithm to convert
    spatial resolution to channels/depth """
    if data_format is None:
        data_format = K.image_data_format()
    data_format = data_format.lower()
    input = _preprocess_conv2d_input(input, data_format)
    out = tf.nn.space_to_depth(input, scale)
    out = _postprocess_conv2d_output(out, data_format)
    return out 

def inception(x, filters):
    """Utility function to implement the inception module.

    # Arguments
        x: input tensor.
        filters: a list of filter sizes.

    # Returns
        Output tensor after applying the inception.
    """
    if len(filters) != 4:
        raise ValueError('filters should have 4 components')
    if len(filters[1]) != 2 or len(filters[2]) != 2:
        raise ValueError('incorrect spec of filters')

    branch1x1 = conv2d_bn(x, filters[0], (1, 1))

    branch3x3 = conv2d_bn(x, filters[1][0], (1, 1))
    branch3x3 = conv2d_bn(branch3x3, filters[1][1], (3, 3))

    branch5x5 = conv2d_bn(x, filters[2][0], (1, 1))
    branch5x5 = conv2d_bn(branch5x5, filters[2][1], (5, 5))

    branchpool = layers.AveragePooling2D(
        pool_size=(3, 3), strides=(1, 1), padding='same')(x)
    branchpool = conv2d_bn(branchpool, filters[3], (1, 1))

    if backend.image_data_format() == 'channels_first':
        concat_axis = 1
    else:
        concat_axis = 3
    x = layers.concatenate(
        [branch1x1, branch3x3, branch5x5, branchpool], axis=concat_axis)
    return x 

def conv2d_bn(x,
              filters,
              kernel_size=(3, 3),
              padding='same',
              strides=(1, 1),
              name=None):
    """Utility function to apply conv + BN.

    # Arguments
        x: input tensor.
        filters: filters in `Conv2D`.
        kernel_size: kernel size of the convolution
        padding: padding mode in `Conv2D`.
        strides: strides in `Conv2D`.
        name: name of the ops; will become `name + '_conv'`
            for the convolution and `name + '_bn'` for the
            batch norm layer.

    # Returns
        Output tensor after applying `Conv2D` and `BatchNormalization`.
    """
    if name is not None:
        bn_name = name + '_bn'
        conv_name = name + '_conv'
    else:
        bn_name = None
        conv_name = None
    if backend.image_data_format() == 'channels_first':
        bn_axis = 1
    else:
        bn_axis = 3
    x = layers.Conv2D(
        filters,
        kernel_size,
        strides=strides,
        padding=padding,
        use_bias=False,
        name=conv_name)(x)
    x = layers.BatchNormalization(axis=bn_axis, name=bn_name)(x)
    x = layers.Activation('relu', name=name)(x)
    return x 

def inception_s2(x, filters):
    """Utility function to implement the 'stride-2' inception module.

    # Arguments
        x: input tensor.
        filters: a list of filter sizes.

    # Returns
        Output tensor after applying the 'stride-2' inception.
    """
    if len(filters) != 2:
        raise ValueError('filters should have 2 components')
    if len(filters[0]) != 2 or len(filters[1]) != 2:
        raise ValueError('incorrect spec of filters')

    branch3x3 = conv2d_bn(x, filters[0][0], (1, 1))
    branch3x3 = conv2d_bn(branch3x3, filters[0][1], (3, 3), strides=(2, 2))

    branch5x5 = conv2d_bn(x, filters[1][0], (1, 1))
    branch5x5 = conv2d_bn(branch5x5, filters[1][1], (3, 3))
    branch5x5 = conv2d_bn(branch5x5, filters[1][1], (3, 3), strides=(2, 2))

    # use MaxPooling2D here
    branchpool = layers.MaxPooling2D(
        pool_size=(3, 3), strides=(2, 2), padding='same')(x)

    concat_axis = 1 if backend.image_data_format() == 'channels_first' else 3
    x = layers.concatenate(
        [branch3x3, branch5x5, branchpool], axis=concat_axis)
    return x 

def inception(x, filters):
    """Utility function to implement the inception module.

    # Arguments
        x: input tensor.
        filters: a list of filter sizes.

    # Returns
        Output tensor after applying the inception.
    """
    if len(filters) != 4:
        raise ValueError('filters should have 4 components')
    if len(filters[1]) != 2 or len(filters[2]) != 2:
        raise ValueError('incorrect spec of filters')

    branch1x1 = conv2d_bn(x, filters[0], (1, 1))

    branch3x3 = conv2d_bn(x, filters[1][0], (1, 1))
    branch3x3 = conv2d_bn(branch3x3, filters[1][1], (3, 3))

    # branch5x5 is implemented with two 3x3 conv2d's
    branch5x5 = conv2d_bn(x, filters[2][0], (1, 1))
    branch5x5 = conv2d_bn(branch5x5, filters[2][1], (3, 3))
    branch5x5 = conv2d_bn(branch5x5, filters[2][1], (3, 3))

    # use AveragePooling2D here
    branchpool = layers.AveragePooling2D(
        pool_size=(3, 3), strides=(1, 1), padding='same')(x)
    branchpool = conv2d_bn(branchpool, filters[3], (1, 1))

    concat_axis = 1 if backend.image_data_format() == 'channels_first' else 3
    x = layers.concatenate(
        [branch1x1, branch3x3, branch5x5, branchpool], axis=concat_axis)
    return x 

def conv2d_bn(x,
              filters,
              kernel_size=(3, 3),
              padding='same',
              strides=(1, 1),
              name=None):
    """Utility function to apply conv + BN.

    # Arguments
        x: input tensor.
        filters: filters in `Conv2D`.
        kernel_size: kernel size of the convolution
        padding: padding mode in `Conv2D`.
        strides: strides in `Conv2D`.
        name: name of the ops; will become `name + '_conv'`
            for the convolution and `name + '_bn'` for the
            batch norm layer.

    # Returns
        Output tensor after applying `Conv2D` and `BatchNormalization`.
    """
    if name is not None:
        bn_name = name + '_bn'
        conv_name = name + '_conv'
    else:
        bn_name = None
        conv_name = None
    bn_axis = 1 if backend.image_data_format() == 'channels_first' else 3
    x = layers.Conv2D(
        filters=filters,
        kernel_size=kernel_size,
        strides=strides,
        padding=padding,
        use_bias=False,
        name=conv_name)(x)
    x = layers.BatchNormalization(axis=bn_axis, name=bn_name)(x)
    x = layers.Activation('relu', name=name)(x)
    return x 

def test_loading(self, _model_4, _config):

        assert backend.image_data_format() == 'channels_first', \
            "Pytorch to Keras parser needs image_data_format == channel_first."

        self.prepare_model(_model_4, _config)

        updates = {
            'tools': {'evaluate_ann': True,
                      'parse': False,
                      'normalize': False,
                      'convert': False,
                      'simulate': False},
            'input': {'model_lib': 'pytorch'},
            'simulation': {'num_to_test': 100,
                           'batch_size': 50}}

        _config.read_dict(updates)

        initialize_simulator(_config)

        normset, testset = get_dataset(_config)

        model_lib = import_module('snntoolbox.parsing.model_libs.' +
                                  _config.get('input', 'model_lib') +
                                  '_input_lib')
        input_model = model_lib.load(_config.get('paths', 'path_wd'),
                                     _config.get('paths', 'filename_ann'))

        # Evaluate input model.
        acc = model_lib.evaluate(input_model['val_fn'],
                                 _config.getint('simulation', 'batch_size'),
                                 _config.getint('simulation', 'num_to_test'),
                                 **testset)

        assert acc >= 0.8 

def parse_convolution(self, layer, attributes):
        attributes['parameters'] = list(layer.get_weights())
        if layer.bias is None:
            attributes['parameters'].insert(1, np.zeros(layer.filters))
            attributes['parameters'] = tuple(attributes['parameters'])
            attributes['use_bias'] = True
        assert layer.data_format == k.image_data_format(), (
            "The input model was setup with image data format '{}', but your "
            "keras config file expects '{}'.".format(layer.data_format,
                                                     k.image_data_format())) 

def _handle_data_format():
    global DIM1_AXIS
    global DIM2_AXIS
    global DIM3_AXIS
    global CHANNEL_AXIS
    if K.image_data_format() == 'channels_last':
        DIM1_AXIS = 1
        DIM2_AXIS = 2
        DIM3_AXIS = 3
        CHANNEL_AXIS = 4
    else:
        CHANNEL_AXIS = 1
        DIM1_AXIS = 2
        DIM2_AXIS = 3
        DIM3_AXIS = 4 

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)