Python keras.backend.ndim() Examples

def get_output(self, train=False):
        def format_shape(shape):
            if K._BACKEND == 'tensorflow':
                def trf(x):
                    try:
                        return int(x)
                    except TypeError:
                        return x

                return map(trf, shape)
            return shape

        X = self.get_input(train)

        in_shape = format_shape(K.shape(X))
        batch_flatten_len = K.prod(in_shape[:2])
        cast_in_shape = (batch_flatten_len, ) + tuple(in_shape[i] for i in range(2, K.ndim(X)))
        
        pre_outs = self.layer(K.reshape(X, cast_in_shape))
        
        out_shape = format_shape(K.shape(pre_outs))
        cast_out_shape = (in_shape[0], in_shape[1]) + tuple(out_shape[i] for i in range(1, K.ndim(pre_outs)))
        
        outputs = K.reshape(pre_outs, cast_out_shape)
        return outputs 

def style_loss(style_image, target_image, style_masks, target_masks):
    '''Calculate style loss between style_image and target_image,
    in all regions.
    '''
    assert 3 == K.ndim(style_image) == K.ndim(target_image)
    assert 3 == K.ndim(style_masks) == K.ndim(target_masks)
    loss = K.variable(0)
    for i in range(num_labels):
        if K.image_data_format() == 'channels_first':
            style_mask = style_masks[i, :, :]
            target_mask = target_masks[i, :, :]
        else:
            style_mask = style_masks[:, :, i]
            target_mask = target_masks[:, :, i]
        loss += region_style_loss(style_image,
                                  target_image, style_mask, target_mask)
    return loss 

def get_realpart(x):
    image_format = K.image_data_format()
    ndim = K.ndim(x)
    input_shape = K.shape(x)

    if (image_format == 'channels_first' and ndim != 3) or ndim == 2:
        input_dim = input_shape[1] // 2
        return x[:, :input_dim]

    input_dim = input_shape[-1] // 2
    if ndim == 3:
        return x[:, :, :input_dim]
    elif ndim == 4:
        return x[:, :, :, :input_dim]
    elif ndim == 5:
        return x[:, :, :, :, :input_dim] 

def get_imagpart(x):
    image_format = K.image_data_format()
    ndim = K.ndim(x)
    input_shape = K.shape(x)

    if (image_format == 'channels_first' and ndim != 3) or ndim == 2:
        input_dim = input_shape[1] // 2
        return x[:, input_dim:]

    input_dim = input_shape[-1] // 2
    if ndim == 3:
        return x[:, :, input_dim:]
    elif ndim == 4:
        return x[:, :, :, input_dim:]
    elif ndim == 5:
        return x[:, :, :, :, input_dim:] 

def _softmax(x, axis=-1, alpha=1):
    """
    building on keras implementation, allow alpha parameter

    Softmax activation function.
    # Arguments
        x : Tensor.
        axis: Integer, axis along which the softmax normalization is applied.
        alpha: a value to multiply all x
    # Returns
        Tensor, output of softmax transformation.
    # Raises
        ValueError: In case `dim(x) == 1`.
    """
    x = alpha * x
    ndim = K.ndim(x)
    if ndim == 2:
        return K.softmax(x)
    elif ndim > 2:
        e = K.exp(x - K.max(x, axis=axis, keepdims=True))
        s = K.sum(e, axis=axis, keepdims=True)
        return e / s
    else:
        raise ValueError('Cannot apply softmax to a tensor that is 1D') 

def sequence_masking(x, mask, mode=0, axis=None):
    """为序列条件mask的函数
    mask: 形如(batch_size, seq_len)的0-1矩阵；
    mode: 如果是0，则直接乘以mask；
          如果是1，则在padding部分减去一个大正数。
    axis: 序列所在轴，默认为1；
    """
    if mask is None or mode not in [0, 1]:
        return x
    else:
        if axis is None:
            axis = 1
        if axis == -1:
            axis = K.ndim(x) - 1
        assert axis > 0, 'axis muse be greater than 0'
        for _ in range(axis - 1):
            mask = K.expand_dims(mask, 1)
        for _ in range(K.ndim(x) - K.ndim(mask) - axis + 1):
            mask = K.expand_dims(mask, K.ndim(mask))
        if mode == 0:
            return x * mask
        else:
            return x - (1 - mask) * 1e12 

def gram_matrix(x):
	"""
	Computes the outer-product of the input tensor x.

	Input
	-----
	- x: input tensor of shape (C x H x W)

	Returns
	-------
	- x . x^T

	Note that this can be computed efficiently if x is reshaped
	as a tensor of shape (C x H*W).
	"""
	# assert K.ndim(x) == 3
	if K.image_dim_ordering() == 'th':
		features = K.batch_flatten(x)
	else:
		features = K.batch_flatten(K.permute_dimensions(x, (2, 0, 1)))
	return K.dot(features, K.transpose(features)) 

def softmax(x, axis=1):
    """Softmax activation function.
    # Arguments
        x : Tensor.
        axis: Integer, axis along which the softmax normalization is applied.
    # Returns
        Tensor, output of softmax transformation.
    # Raises
        ValueError: In case `dim(x) == 1`.
    """
    ndim = K.ndim(x)
    if ndim == 2:
        return K.softmax(x)
    elif ndim > 2:
        e = K.exp(x - K.max(x, axis=axis, keepdims=True))
        s = K.sum(e, axis=axis, keepdims=True)
        return e / s
    else:
        raise ValueError('Cannot apply softmax to a tensor that is 1D') 

def softmax(x, axis=1):
    """Softmax activation function.
    # Arguments
        x : Tensor.
        axis: Integer, axis along which the softmax normalization is applied.
    # Returns
        Tensor, output of softmax transformation.
    # Raises
        ValueError: In case `dim(x) == 1`.
    """
    ndim = K.ndim(x)
    if ndim == 2:
        return K.softmax(x)
    elif ndim > 2:
        e = K.exp(x - K.max(x, axis=axis, keepdims=True))
        s = K.sum(e, axis=axis, keepdims=True)
        return e / s
    else:
        raise ValueError('Cannot apply softmax to a tensor that is 1D') 

def call(self, X, mask=None):
        if mask is not None:
            assert K.ndim(mask) == 2, 'Input mask to CRF must have dim 2 if not None'

        if self.test_mode == 'viterbi':
            test_output = self.viterbi_decoding(X, mask)
        else:
            test_output = self.get_marginal_prob(X, mask)

        self.uses_learning_phase = True
        if self.learn_mode == 'join':
            train_output = K.zeros_like(K.dot(X, self.kernel))
            out = K.in_train_phase(train_output, test_output)
        else:
            if self.test_mode == 'viterbi':
                train_output = self.get_marginal_prob(X, mask)
                out = K.in_train_phase(train_output, test_output)
            else:
                out = test_output
        return out 

def __init__(self, output_dim, init='glorot_uniform', activation='relu',weights=None,
            W_regularizer=None, b_regularizer=None, activity_regularizer=None,
            W_constraint=None, b_constraint=None, input_dim=None, **kwargs):
        self.W_initializer = initializers.get(init)
        self.b_initializer = initializers.get('zeros')
        self.activation = activations.get(activation)
        self.output_dim = output_dim
        self.input_dim = input_dim

        self.W_regularizer = regularizers.get(W_regularizer)
        self.b_regularizer = regularizers.get(b_regularizer)
        self.activity_regularizer = regularizers.get(activity_regularizer)

        self.W_constraint = constraints.get(W_constraint)
        self.b_constraint = constraints.get(b_constraint)
        self.initial_weights = weights
        self.input_spec = InputSpec(ndim=2)

        if self.input_dim:
            kwargs['input_shape'] = (self.input_dim,)
        super(SparseFullyConnectedLayer, self).__init__(**kwargs) 

def style_loss(style_image, target_image, style_masks, target_masks):
    '''Calculate style loss between style_image and target_image,
    in all regions.
    '''
    assert 3 == K.ndim(style_image) == K.ndim(target_image)
    assert 3 == K.ndim(style_masks) == K.ndim(target_masks)
    loss = K.variable(0)
    for i in range(num_labels):
        if K.image_data_format() == 'channels_first':
            style_mask = style_masks[i, :, :]
            target_mask = target_masks[i, :, :]
        else:
            style_mask = style_masks[:, :, i]
            target_mask = target_masks[:, :, i]
        loss += region_style_loss(style_image,
                                  target_image, style_mask, target_mask)
    return loss 

def region_style_loss(style_image, target_image, style_mask, target_mask):
    '''Calculate style loss between style_image and target_image,
    for one common region specified by their (boolean) masks
    '''
    assert 3 == K.ndim(style_image) == K.ndim(target_image)
    assert 2 == K.ndim(style_mask) == K.ndim(target_mask)
    if K.image_data_format() == 'channels_first':
        masked_style = style_image * style_mask
        masked_target = target_image * target_mask
        num_channels = K.shape(style_image)[0]
    else:
        masked_style = K.permute_dimensions(
            style_image, (2, 0, 1)) * style_mask
        masked_target = K.permute_dimensions(
            target_image, (2, 0, 1)) * target_mask
        num_channels = K.shape(style_image)[-1]
    num_channels = K.cast(num_channels, dtype='float32')
    s = gram_matrix(masked_style) / K.mean(style_mask) / num_channels
    c = gram_matrix(masked_target) / K.mean(target_mask) / num_channels
    return K.mean(K.square(s - c)) 

def style_loss(style_image, target_image, style_masks, target_masks):
    '''Calculate style loss between style_image and target_image,
    in all regions.
    '''
    assert 3 == K.ndim(style_image) == K.ndim(target_image)
    assert 3 == K.ndim(style_masks) == K.ndim(target_masks)
    loss = K.variable(0)
    for i in range(num_labels):
        if K.image_data_format() == 'channels_first':
            style_mask = style_masks[i, :, :]
            target_mask = target_masks[i, :, :]
        else:
            style_mask = style_masks[:, :, i]
            target_mask = target_masks[:, :, i]
        loss += region_style_loss(style_image,
                                  target_image, style_mask, target_mask)
    return loss 

def total_variation_loss(x):
    assert 4 == K.ndim(x)
    if K.image_data_format() == 'channels_first':
        a = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] -
                     x[:, :, 1:, :img_ncols - 1])
        b = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] -
                     x[:, :, :img_nrows - 1, 1:])
    else:
        a = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] -
                     x[:, 1:, :img_ncols - 1, :])
        b = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] -
                     x[:, :img_nrows - 1, 1:, :])
    return K.sum(K.pow(a + b, 1.25))

# Overall loss is the weighted sum of content_loss, style_loss and tv_loss
# Each individual loss uses features from image/mask models. 

def style_loss(style_image, target_image, style_masks, target_masks):
    '''Calculate style loss between style_image and target_image,
    in all regions.
    '''
    assert 3 == K.ndim(style_image) == K.ndim(target_image)
    assert 3 == K.ndim(style_masks) == K.ndim(target_masks)
    loss = K.variable(0)
    for i in range(num_labels):
        if K.image_data_format() == 'channels_first':
            style_mask = style_masks[i, :, :]
            target_mask = target_masks[i, :, :]
        else:
            style_mask = style_masks[:, :, i]
            target_mask = target_masks[:, :, i]
        loss += region_style_loss(style_image,
                                  target_image, style_mask, target_mask)
    return loss 

def total_variation_loss(x):
    assert 4 == K.ndim(x)
    if K.image_data_format() == 'channels_first':
        a = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] -
                     x[:, :, 1:, :img_ncols - 1])
        b = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] -
                     x[:, :, :img_nrows - 1, 1:])
    else:
        a = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] -
                     x[:, 1:, :img_ncols - 1, :])
        b = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] -
                     x[:, :img_nrows - 1, 1:, :])
    return K.sum(K.pow(a + b, 1.25))

# Overall loss is the weighted sum of content_loss, style_loss and tv_loss
# Each individual loss uses features from image/mask models. 

def region_style_loss(style_image, target_image, style_mask, target_mask):
    '''Calculate style loss between style_image and target_image,
    for one common region specified by their (boolean) masks
    '''
    assert 3 == K.ndim(style_image) == K.ndim(target_image)
    assert 2 == K.ndim(style_mask) == K.ndim(target_mask)
    if K.image_data_format() == 'channels_first':
        masked_style = style_image * style_mask
        masked_target = target_image * target_mask
        num_channels = K.shape(style_image)[0]
    else:
        masked_style = K.permute_dimensions(
            style_image, (2, 0, 1)) * style_mask
        masked_target = K.permute_dimensions(
            target_image, (2, 0, 1)) * target_mask
        num_channels = K.shape(style_image)[-1]
    num_channels = K.cast(num_channels, dtype='float32')
    s = gram_matrix(masked_style) / K.mean(style_mask) / num_channels
    c = gram_matrix(masked_target) / K.mean(target_mask) / num_channels
    return K.mean(K.square(s - c)) 

def style_loss(style_image, target_image, style_masks, target_masks):
    '''Calculate style loss between style_image and target_image,
    in all regions.
    '''
    assert 3 == K.ndim(style_image) == K.ndim(target_image)
    assert 3 == K.ndim(style_masks) == K.ndim(target_masks)
    loss = K.variable(0)
    for i in range(num_labels):
        if K.image_data_format() == 'channels_first':
            style_mask = style_masks[i, :, :]
            target_mask = target_masks[i, :, :]
        else:
            style_mask = style_masks[:, :, i]
            target_mask = target_masks[:, :, i]
        loss += region_style_loss(style_image,
                                  target_image, style_mask, target_mask)
    return loss 

def total_variation_loss(x):
    assert 4 == K.ndim(x)
    if K.image_data_format() == 'channels_first':
        a = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] -
                     x[:, :, 1:, :img_ncols - 1])
        b = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] -
                     x[:, :, :img_nrows - 1, 1:])
    else:
        a = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] -
                     x[:, 1:, :img_ncols - 1, :])
        b = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] -
                     x[:, :img_nrows - 1, 1:, :])
    return K.sum(K.pow(a + b, 1.25))

# Overall loss is the weighted sum of content_loss, style_loss and tv_loss
# Each individual loss uses features from image/mask models. 

def build(self, input_shape):
        assert len(input_shape) == 2
        input_dim = input_shape[1]
        #self.input_spec = InputSpec(dtype=K.floatx(), shape=(None, input_dim))
        self.input_spec = InputSpec(ndim=2, axes={1: input_dim})

        self.W = self.add_weight(
                shape=(input_dim, self.output_dim),
                initializer=self.W_initializer,
                name='SparseFullyConnected_W',
                regularizer=self.W_regularizer,
                constraint=self.W_constraint)
        self.b = self.add_weight(
                shape=(self.output_dim,),
                initializer=self.b_initializer,
                name='SparseFullyConnected_b',
                regularizer=self.b_regularizer,
                constraint=self.b_constraint)


        if self.initial_weights is not None:
            self.set_weights(self.initial_weights)
            del self.initial_weights
        #self.built = True
        #super(SparseFullyConnectedLayer, self).build(input_shape) 

def total_variation_loss(x):
    assert 4 == K.ndim(x)
    if K.image_data_format() == 'channels_first':
        a = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] -
                     x[:, :, 1:, :img_ncols - 1])
        b = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] -
                     x[:, :, :img_nrows - 1, 1:])
    else:
        a = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] -
                     x[:, 1:, :img_ncols - 1, :])
        b = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] -
                     x[:, :img_nrows - 1, 1:, :])
    return K.sum(K.pow(a + b, 1.25))

# Overall loss is the weighted sum of content_loss, style_loss and tv_loss
# Each individual loss uses features from image/mask models. 

def gram_matrix(x):
    assert K.ndim(x) == 3
    if K.image_data_format() == 'channels_first':
        features = K.batch_flatten(x)
    else:
        features = K.batch_flatten(K.permute_dimensions(x, (2, 0, 1)))
    gram = K.dot(features, K.transpose(features))
    return gram

# the "style loss" is designed to maintain
# the style of the reference image in the generated image.
# It is based on the gram matrices (which capture style) of
# feature maps from the style reference image
# and from the generated image 

def build(self, input_shape):
        self.input_spec = InputSpec(ndim=len(input_shape),
                                    axes={self.axis: input_shape[self.axis]})
        shape = (input_shape[self.axis],)

        self.gamma = self.add_weight(shape,
                                     initializer=self.gamma_init,
                                     regularizer=self.gamma_regularizer,
                                     name='{}_gamma'.format(self.name))
        self.beta = self.add_weight(shape,
                                    initializer=self.beta_init,
                                    regularizer=self.beta_regularizer,
                                    name='{}_beta'.format(self.name))

        self.built = True 

def gram_matrix(x):
    assert K.ndim(x) == 3
    if K.image_data_format() == 'channels_first':
        features = K.batch_flatten(x)
    else:
        features = K.batch_flatten(K.permute_dimensions(x, (2, 0, 1)))
    gram = K.dot(features, K.transpose(features))
    return gram

# the "style loss" is designed to maintain
# the style of the reference image in the generated image.
# It is based on the gram matrices (which capture style) of
# feature maps from the style reference image
# and from the generated image 

def style_loss(style, combination):
    assert K.ndim(style) == 3
    assert K.ndim(combination) == 3
    S = gram_matrix(style)
    C = gram_matrix(combination)
    channels = 3
    size = img_nrows * img_ncols
    return K.sum(K.square(S - C)) / (4. * (channels ** 2) * (size ** 2))

# an auxiliary loss function
# designed to maintain the "content" of the
# base image in the generated image 

def total_variation_loss(x):
    assert K.ndim(x) == 4
    if K.image_data_format() == 'channels_first':
        a = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] - x[:, :, 1:, :img_ncols - 1])
        b = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] - x[:, :, :img_nrows - 1, 1:])
    else:
        a = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] - x[:, 1:, :img_ncols - 1, :])
        b = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] - x[:, :img_nrows - 1, 1:, :])
    return K.sum(K.pow(a + b, 1.25))

# combine these loss functions into a single scalar 

def kmeans(xs, k):
    assert xs.ndim == 2
    try:
        from sklearn.cluster import k_means
        _, labels, _ = k_means(xs.astype('float64'), k)
    except ImportError:
        from scipy.cluster.vq import kmeans2
        _, labels = kmeans2(xs, k, missing='raise')
    return labels 

def getpart_output_shape(input_shape):
    returned_shape = list(input_shape[:])
    image_format = K.image_data_format()
    ndim = len(returned_shape)

    if (image_format == 'channels_first' and ndim != 3) or ndim == 2:
        axis = 1
    else:
        axis = -1

    returned_shape[axis] = returned_shape[axis] // 2

    return tuple(returned_shape) 

def gram_matrix(x):
    assert K.ndim(x) == 3
    features = K.batch_flatten(x)
    gram = K.dot(features, K.transpose(features))
    return gram