Python keras.backend.int_shape() Examples

The following are 30 code examples of keras.backend.int_shape(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module keras.backend , or try the search function .
Example #1
Source File: timeception.py    From deep-smoke-machine with BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up
def timeception_layers(tensor, n_layers=4, n_groups=8, is_dilated=True):
    input_shape = K.int_shape(tensor)
    assert len(input_shape) == 5

    expansion_factor = 1.25
    _, n_timesteps, side_dim, side_dim, n_channels_in = input_shape

    # how many layers of timeception
    for i in range(n_layers):
        layer_num = i + 1

        # get details about grouping
        n_channels_per_branch, n_channels_out = __get_n_channels_per_branch(n_groups, expansion_factor, n_channels_in)

        # temporal conv per group
        tensor = __grouped_convolutions(tensor, n_groups, n_channels_per_branch, is_dilated, layer_num)

        # downsample over time
        tensor = MaxPooling3D(pool_size=(2, 1, 1), name='maxpool_tc%d' % (layer_num))(tensor)
        n_channels_in = n_channels_out

    return tensor 
Example #2
Source File: timeception.py    From deep-smoke-machine with BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up
def __call_timeception_layers(self, tensor, n_layers, n_groups, expansion_factor):
        input_shape = K.int_shape(tensor)
        assert len(input_shape) == 5

        _, n_timesteps, side_dim, side_dim, n_channels_in = input_shape

        # how many layers of timeception
        for i in range(n_layers):
            layer_num = i + 1

            # get details about grouping
            n_channels_per_branch, n_channels_out = self.__get_n_channels_per_branch(n_groups, expansion_factor, n_channels_in)

            # temporal conv per group
            tensor = self.__call_grouped_convolutions(tensor, n_groups, n_channels_per_branch, layer_num)

            # downsample over time
            tensor = getattr(self, 'maxpool_tc%d' % (layer_num))(tensor)
            n_channels_in = n_channels_out

        return tensor 
Example #3
Source File: timeception.py    From timeception with GNU General Public License v3.0 6 votes vote down vote up
def timeception_layers(tensor, n_layers=4, n_groups=8, is_dilated=True):
    input_shape = K.int_shape(tensor)
    assert len(input_shape) == 5

    expansion_factor = 1.25
    _, n_timesteps, side_dim, side_dim, n_channels_in = input_shape

    # how many layers of timeception
    for i in range(n_layers):
        layer_num = i + 1

        # get details about grouping
        n_channels_per_branch, n_channels_out = __get_n_channels_per_branch(n_groups, expansion_factor, n_channels_in)

        # temporal conv per group
        tensor = __grouped_convolutions(tensor, n_groups, n_channels_per_branch, is_dilated, layer_num)

        # downsample over time
        tensor = MaxPooling3D(pool_size=(2, 1, 1), name='maxpool_tc%d' % (layer_num))(tensor)
        n_channels_in = n_channels_out

    return tensor 
Example #4
Source File: timeception.py    From timeception with GNU General Public License v3.0 6 votes vote down vote up
def __call_timeception_layers(self, tensor, n_layers, n_groups, expansion_factor):
        input_shape = K.int_shape(tensor)
        assert len(input_shape) == 5

        _, n_timesteps, side_dim, side_dim, n_channels_in = input_shape

        # how many layers of timeception
        for i in range(n_layers):
            layer_num = i + 1

            # get details about grouping
            n_channels_per_branch, n_channels_out = self.__get_n_channels_per_branch(n_groups, expansion_factor, n_channels_in)

            # temporal conv per group
            tensor = self.__call_grouped_convolutions(tensor, n_groups, n_channels_per_branch, layer_num)

            # downsample over time
            tensor = getattr(self, 'maxpool_tc%d' % (layer_num))(tensor)
            n_channels_in = n_channels_out

        return tensor 
Example #5
Source File: chapter_06_001.py    From Python-Deep-Learning-SE with MIT License 6 votes vote down vote up
def sampling(args: tuple):
    """
    Reparameterization trick by sampling z from unit Gaussian
    :param args: (tensor, tensor) mean and log of variance of q(z|x)
    :returns tensor: sampled latent vector z
    """

    # unpack the input tuple
    z_mean, z_log_var = args

    # mini-batch size
    mb_size = K.shape(z_mean)[0]

    # latent space size
    dim = K.int_shape(z_mean)[1]

    # random normal vector with mean=0 and std=1.0
    epsilon = K.random_normal(shape=(mb_size, dim))

    return z_mean + K.exp(0.5 * z_log_var) * epsilon 
Example #6
Source File: models.py    From SeqGAN with MIT License 6 votes vote down vote up
def Highway(x, num_layers=1, activation='relu', name_prefix=''):
    '''
    Layer wrapper function for Highway network
    # Arguments:
        x: tensor, shape = (B, input_size)
    # Optional Arguments:
        num_layers: int, dafault is 1, the number of Highway network layers
        activation: keras activation, default is 'relu'
        name_prefix: str, default is '', layer name prefix
    # Returns:
        out: tensor, shape = (B, input_size)
    '''
    input_size = K.int_shape(x)[1]
    for i in range(num_layers):
        gate_ratio_name = '{}Highway/Gate_ratio_{}'.format(name_prefix, i)
        fc_name = '{}Highway/FC_{}'.format(name_prefix, i)
        gate_name = '{}Highway/Gate_{}'.format(name_prefix, i)

        gate_ratio = Dense(input_size, activation='sigmoid', name=gate_ratio_name)(x)
        fc = Dense(input_size, activation=activation, name=fc_name)(x)
        x = Lambda(lambda args: args[0] * args[2] + args[1] * (1 - args[2]), name=gate_name)([fc, x, gate_ratio])
    return x 
Example #7
Source File: recurrent.py    From keras_bn_library with MIT License 6 votes vote down vote up
def get_constants(self, x):
		constants = []
		if 0 < self.dropout_U < 1:
			ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
			ones = K.tile(ones, (1, self.input_dim))
			B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(4)]
			constants.append(B_U)
		else:
			constants.append([K.cast_to_floatx(1.) for _ in range(4)])

		if 0 < self.dropout_W < 1:
			input_shape = K.int_shape(x)
			input_dim = input_shape[-1]
			ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
			ones = K.tile(ones, (1, int(input_dim)))
			B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(4)]
			constants.append(B_W)
		else:
			constants.append([K.cast_to_floatx(1.) for _ in range(4)])
		return constants 
Example #8
Source File: vae.py    From pyod with BSD 2-Clause "Simplified" License 6 votes vote down vote up
def sampling(self, args):
        """Reparametrisation by sampling from Gaussian, N(0,I)
        To sample from epsilon = Norm(0,I) instead of from likelihood Q(z|X)
        with latent variables z: z = z_mean + sqrt(var) * epsilon

        Parameters
        ----------
        args : tensor
            Mean and log of variance of Q(z|X).
    
        Returns
        -------
        z : tensor
            Sampled latent variable.
        """

        z_mean, z_log = args
        batch = K.shape(z_mean)[0]  # batch size
        dim = K.int_shape(z_mean)[1]  # latent dimension
        epsilon = K.random_normal(shape=(batch, dim))  # mean=0, std=1.0

        return z_mean + K.exp(0.5 * z_log) * epsilon 
Example #9
Source File: instance_normalization.py    From Coloring-greyscale-images with MIT License 6 votes vote down vote up
def call(self, inputs, training=None):
        input_shape = K.int_shape(inputs)
        reduction_axes = list(range(0, len(input_shape)))

        if (self.axis is not None):
            del reduction_axes[self.axis]

        del reduction_axes[0]

        mean = K.mean(inputs, reduction_axes, keepdims=True)
        stddev = K.std(inputs, reduction_axes, keepdims=True) + self.epsilon
        normed = (inputs - mean) / stddev

        broadcast_shape = [1] * len(input_shape)
        if self.axis is not None:
            broadcast_shape[self.axis] = input_shape[self.axis]

        if self.scale:
            broadcast_gamma = K.reshape(self.gamma, broadcast_shape)
            normed = normed * broadcast_gamma
        if self.center:
            broadcast_beta = K.reshape(self.beta, broadcast_shape)
            normed = normed + broadcast_beta
        return normed 
Example #10
Source File: decoders.py    From keras-fcn with MIT License 6 votes vote down vote up
def VGGUpsampler(pyramid, scales, classes, weight_decay=0.):
    """A Functional upsampler for the VGG Nets.

    :param: pyramid: A list of features in pyramid, scaling from large
                    receptive field to small receptive field.
                    The bottom of the pyramid is the input image.
    :param: scales: A list of weights for each of the feature map in the
                    pyramid, sorted in the same order as the pyramid.
    :param: classes: Integer, number of classes.
    """
    if len(scales) != len(pyramid) - 1:
        raise ValueError('`scales` needs to match the length of'
                         '`pyramid` - 1.')
    blocks = []

    for i in range(len(pyramid) - 1):
        block_name = 'feat{}'.format(i + 1)
        block = vgg_upsampling(classes=classes,
                               target_shape=K.int_shape(pyramid[i + 1]),
                               scale=scales[i],
                               weight_decay=weight_decay,
                               block_name=block_name)
        blocks.append(block)

    return Decoder(pyramid=pyramid[:-1], blocks=blocks) 
Example #11
Source File: test_decoders.py    From keras-fcn with MIT License 6 votes vote down vote up
def test_vgg_decoder():
    if K.image_data_format() == 'channels_last':
        inputs = Input(shape=(500, 500, 3))
        pool3 = Input(shape=(88, 88, 256))
        pool4 = Input(shape=(44, 44, 512))
        drop7 = Input(shape=(16, 16, 4096))
        score_shape = (None, 500, 500, 21)
    else:
        inputs = Input(shape=(3, 500, 500))
        pool3 = Input(shape=(256, 88, 88))
        pool4 = Input(shape=(512, 44, 44))
        drop7 = Input(shape=(4096, 16, 16))
        score_shape = (None, 21, 500, 500)
    pyramid = [drop7, pool4, pool3, inputs]
    scales = [1., 1e-2, 1e-4]
    score = VGGDecoder(pyramid, scales, classes=21)
    assert K.int_shape(score) == score_shape 
Example #12
Source File: test_blocks.py    From keras-fcn with MIT License 6 votes vote down vote up
def test_vgg_conv():
    if K.image_data_format() == 'channels_first':
        x = Input(shape=(3, 224, 224))
        y1_shape = (None, 64, 112, 112)
        y2_shape = (None, 128, 56, 56)
    else:
        x = Input(shape=(224, 224, 3))
        y1_shape = (None, 112, 112, 64)
        y2_shape = (None, 56, 56, 128)

    block1 = vgg_conv(filters=64, convs=2, block_name='block1')
    y = block1(x)
    assert K.int_shape(y) == y1_shape

    block2 = vgg_conv(filters=128, convs=2, block_name='block2')
    y = block2(y)
    assert K.int_shape(y) == y2_shape 
Example #13
Source File: normalizations.py    From se_relativisticgan with MIT License 6 votes vote down vote up
def call(self, inputs, training=None):
        input_shape = K.int_shape(inputs)
        reduction_axes = list(range(0, len(input_shape)))

        if (self.axis is not None):
            del reduction_axes[self.axis]

        del reduction_axes[0]

        mean = K.mean(inputs, reduction_axes, keepdims=True)
        stddev = K.std(inputs, reduction_axes, keepdims=True) + self.epsilon
        normed = (inputs - mean) / stddev

        broadcast_shape = [1] * len(input_shape)
        if self.axis is not None:
            broadcast_shape[self.axis] = input_shape[self.axis]

        if self.scale:
            broadcast_gamma = K.reshape(self.gamma, broadcast_shape)
            normed = normed * broadcast_gamma
        if self.center:
            broadcast_beta = K.reshape(self.beta, broadcast_shape)
            normed = normed + broadcast_beta
        return normed 
Example #14
Source File: hourglass.py    From keras-centernet with MIT License 6 votes vote down vote up
def residual(_x, out_dim, name, stride=1):
  shortcut = _x
  num_channels = K.int_shape(shortcut)[-1]
  _x = ZeroPadding2D(padding=1, name=name + '.pad1')(_x)
  _x = Conv2D(out_dim, 3, strides=stride, use_bias=False, name=name + '.conv1')(_x)
  _x = BatchNormalization(epsilon=1e-5, name=name + '.bn1')(_x)
  _x = Activation('relu', name=name + '.relu1')(_x)

  _x = Conv2D(out_dim, 3, padding='same', use_bias=False, name=name + '.conv2')(_x)
  _x = BatchNormalization(epsilon=1e-5, name=name + '.bn2')(_x)

  if num_channels != out_dim or stride != 1:
    shortcut = Conv2D(out_dim, 1, strides=stride, use_bias=False, name=name + '.shortcut.0')(
        shortcut)
    shortcut = BatchNormalization(epsilon=1e-5, name=name + '.shortcut.1')(shortcut)

  _x = Add(name=name + '.add')([_x, shortcut])
  _x = Activation('relu', name=name + '.relu')(_x)
  return _x 
Example #15
Source File: model_utils.py    From image-segmentation-keras with MIT License 6 votes vote down vote up
def resize_image(inp,  s, data_format):

    try:

        return Lambda(lambda x: K.resize_images(x,
                                                height_factor=s[0],
                                                width_factor=s[1],
                                                data_format=data_format,
                                                interpolation='bilinear'))(inp)

    except Exception as e:
        # if keras is old, then rely on the tf function
        # Sorry theano/cntk users!!!
        assert data_format == 'channels_last'
        assert IMAGE_ORDERING == 'channels_last'

        import tensorflow as tf

        return Lambda(
            lambda x: tf.image.resize_images(
                x, (K.int_shape(x)[1]*s[0], K.int_shape(x)[2]*s[1]))
        )(inp) 
Example #16
Source File: pspnet.py    From image-segmentation-keras with MIT License 6 votes vote down vote up
def pool_block(feats, pool_factor):

    if IMAGE_ORDERING == 'channels_first':
        h = K.int_shape(feats)[2]
        w = K.int_shape(feats)[3]
    elif IMAGE_ORDERING == 'channels_last':
        h = K.int_shape(feats)[1]
        w = K.int_shape(feats)[2]

    pool_size = strides = [
        int(np.round(float(h) / pool_factor)),
        int(np.round(float(w) / pool_factor))]

    x = AveragePooling2D(pool_size, data_format=IMAGE_ORDERING,
                         strides=strides, padding='same')(feats)
    x = Conv2D(512, (1, 1), data_format=IMAGE_ORDERING,
               padding='same', use_bias=False)(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = resize_image(x, strides, data_format=IMAGE_ORDERING)

    return x 
Example #17
Source File: custom_objects.py    From keras_mixnets with MIT License 5 votes vote down vote up
def call(self, inputs, **kwargs):
        if len(self._layers) == 1:
            return self._layers[0](inputs)

        filters = K.int_shape(inputs)[self._channel_axis]
        splits = self._split_channels(filters, self.groups)
        x_splits = tf.split(inputs, splits, self._channel_axis)
        x_outputs = [c(x) for x, c in zip(x_splits, self._layers)]
        x = layers.concatenate(x_outputs, axis=self._channel_axis)
        return x 
Example #18
Source File: mixnets.py    From keras_mixnets with MIT License 5 votes vote down vote up
def __call__(self, inputs):
        filters = K.int_shape(inputs)[self._channel_axis]
        grouped_op = GroupConvolution(filters, self.kernels, groups=len(self.kernels),
                                      type='depthwise_conv', conv_kwargs=self._conv_kwargs)
        x = grouped_op(inputs)
        return x


# Obtained from https://github.com/tensorflow/tpu/blob/master/models/official/mnasnet/mixnet/mixnet_model.py 
Example #19
Source File: hlnet.py    From Face-skin-hair-segmentaiton-and-skin-color-evaluation with Apache License 2.0 5 votes vote down vote up
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))

    x = DepthwiseConv2D(kernel, strides=(
        s, s), depth_multiplier=1, padding='same')(x)
    x = BatchNormalization(axis=channel_axis)(x)
    # relu6
    x = ReLU(max_value=6)(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 
Example #20
Source File: losses.py    From gandlf with MIT License 5 votes vote down vote up
def rbf_moment_matching(y_true, y_pred, sigmas=[2, 5, 10, 20, 40, 80]):
    """Generative moment matching loss with RBF kernel.

    Reference: https://arxiv.org/abs/1502.02761
    """

    warnings.warn('Moment matching loss is still in development.')

    if len(K.int_shape(y_pred)) != 2 or len(K.int_shape(y_true)) != 2:
        raise ValueError('RBF Moment Matching function currently only works '
                         'for outputs with shape (batch_size, num_features).'
                         'Got y_true="%s" and y_pred="%s".' %
                         (str(K.int_shape(y_pred)), str(K.int_shape(y_true))))

    sigmas = list(sigmas) if isinstance(sigmas, (list, tuple)) else [sigmas]

    x = K.concatenate([y_pred, y_true], 0)

    # Performs dot product between all combinations of rows in X.
    xx = K.dot(x, K.transpose(x))  # (batch_size, batch_size)

    # Performs dot product of all rows with themselves.
    x2 = K.sum(x * x, 1, keepdims=True)  # (batch_size, None)

    # Gets exponent entries of the RBF kernel (without sigmas).
    exponent = xx - 0.5 * x2 - 0.5 * K.transpose(x2)

    # Applies all the sigmas.
    total_loss = None
    for sigma in sigmas:
        kernel_val = K.exp(exponent / sigma)
        loss = K.sum(kernel_val)
        total_loss = loss if total_loss is None else loss + total_loss

    return total_loss 
Example #21
Source File: attention.py    From gandlf with MIT License 5 votes vote down vote up
def __init__(self, layer, attention, attn_activation='tanh',
                 attn_gate_func='sigmoid', W_regularizer=None,
                 b_regularizer=None, **kwargs):

        if not isinstance(layer, keras.layers.Recurrent):
            raise ValueError('The RecurrentAttention wrapper only works on '
                             'recurrent layers.')

        # Should know this so that we can handle multiple hidden states.
        self._wraps_lstm = isinstance(layer, keras.layers.LSTM)

        if not hasattr(attention, '_keras_shape'):
            raise ValueError('Attention should be a Keras tensor.')

        if len(K.int_shape(attention)) != 2:
            raise ValueError('The attention input for RecurrentAttention2D '
                             'should be a tensor with shape (batch_size, '
                             'num_features). Got shape=%s.' %
                             str(K.int_shape(attention)))

        self.supports_masking = True
        self.attention = attention
        self.attn_activation = keras.activations.get(attn_activation)
        self.attn_gate_func = keras.activations.get(attn_gate_func)

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

        super(RecurrentAttention1D, self).__init__(layer, **kwargs) 
Example #22
Source File: attention.py    From gandlf with MIT License 5 votes vote down vote up
def __init__(self, layer, attention, time_dist_activation='softmax',
                 attn_gate_func='sigmoid', W_regularizer=None,
                 b_regularizer=None, **kwargs):

        if not isinstance(layer, keras.layers.Recurrent):
            raise ValueError('The RecurrentAttention wrapper only works on '
                             'recurrent layers.')

        # Should know this so that we can handle multiple hidden states.
        self._wraps_lstm = isinstance(layer, keras.layers.LSTM)

        if not hasattr(attention, '_keras_shape'):
            raise ValueError('Attention should be a Keras tensor.')

        if len(K.int_shape(attention)) != 3:
            raise ValueError('The attention input for RecurrentAttention2D '
                             'should be a tensor with shape (batch_size, '
                             'num_timesteps, num_features). Got shape=%s.' %
                             str(K.int_shape(attention)))

        self.supports_masking = True
        self.attention = attention

        self.time_dist_activation = keras.activations.get(time_dist_activation)
        self.attn_gate_func = keras.activations.get(attn_gate_func)

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

        super(RecurrentAttention2D, self).__init__(layer, **kwargs) 
Example #23
Source File: attention.py    From gandlf with MIT License 5 votes vote down vote up
def build(self, input_shape):
        assert input_shape >= 3
        self.input_spec = [keras.engine.InputSpec(shape=input_shape)]

        # Builds the wrapped layer.
        if not self.layer.built:
            self.layer.build(input_shape)

        super(RecurrentAttention2D, self).build()

        num_attn_timesteps, num_attn_feats = K.int_shape(self.attention)[1:]
        output_dim = self.layer.output_dim

        self.attn_U_t = self.add_weight((output_dim, num_attn_timesteps),
                                   initializer=self.layer.inner_init,
                                   name='{}_attn_U_t'.format(self.name),
                                   regularizer=self.W_regularizer)
        self.attn_b_t = self.add_weight((num_attn_timesteps,),
                                   initializer='zero',
                                   name='{}_attn_b_t'.format(self.name),
                                   regularizer=self.b_regularizer)

        self.attn_U_a = self.add_weight((num_attn_feats, output_dim),
                                   initializer=self.layer.inner_init,
                                   name='{}_attn_U_a'.format(self.name),
                                   regularizer=self.W_regularizer)
        self.attn_b_a = self.add_weight((output_dim,),
                                   initializer='zero',
                                   name='{}_attn_b_a'.format(self.name),
                                   regularizer=self.b_regularizer)

        self.trainable_weights = [self.attn_U_t, self.attn_b_t,
                                  self.attn_U_a, self.attn_b_a] 
Example #24
Source File: FixedBatchNormalization.py    From FasterRCNN_KERAS with Apache License 2.0 5 votes vote down vote up
def call(self, x, mask=None):

        assert self.built, 'Layer must be built before being called'
        input_shape = K.int_shape(x)

        reduction_axes = list(range(len(input_shape)))
        del reduction_axes[self.axis]
        broadcast_shape = [1] * len(input_shape)
        broadcast_shape[self.axis] = input_shape[self.axis]

        if sorted(reduction_axes) == range(K.ndim(x))[:-1]:
            x_normed = K.batch_normalization(
                x, self.running_mean, self.running_std,
                self.beta, self.gamma,
                epsilon=self.epsilon)
        else:
            # need broadcasting
            broadcast_running_mean = K.reshape(self.running_mean, broadcast_shape)
            broadcast_running_std = K.reshape(self.running_std, broadcast_shape)
            broadcast_beta = K.reshape(self.beta, broadcast_shape)
            broadcast_gamma = K.reshape(self.gamma, broadcast_shape)
            x_normed = K.batch_normalization(
                x, broadcast_running_mean, broadcast_running_std,
                broadcast_beta, broadcast_gamma,
                epsilon=self.epsilon)

        return x_normed 
Example #25
Source File: model.py    From dataiku-contrib with Apache License 2.0 5 votes vote down vote up
def mrcnn_bbox_loss_graph(target_bbox, target_class_ids, pred_bbox):
    """Loss for Mask R-CNN bounding box refinement.
    target_bbox: [batch, num_rois, (dy, dx, log(dh), log(dw))]
    target_class_ids: [batch, num_rois]. Integer class IDs.
    pred_bbox: [batch, num_rois, num_classes, (dy, dx, log(dh), log(dw))]
    """
    # Reshape to merge batch and roi dimensions for simplicity.
    target_class_ids = K.reshape(target_class_ids, (-1,))
    target_bbox = K.reshape(target_bbox, (-1, 4))
    pred_bbox = K.reshape(pred_bbox, (-1, K.int_shape(pred_bbox)[2], 4))

    # Only positive ROIs contribute to the loss. And only
    # the right class_id of each ROI. Get their indices.
    positive_roi_ix = tf.where(target_class_ids > 0)[:, 0]
    positive_roi_class_ids = tf.cast(
        tf.gather(target_class_ids, positive_roi_ix), tf.int64)
    indices = tf.stack([positive_roi_ix, positive_roi_class_ids], axis=1)

    # Gather the deltas (predicted and true) that contribute to loss
    target_bbox = tf.gather(target_bbox, positive_roi_ix)
    pred_bbox = tf.gather_nd(pred_bbox, indices)

    # Smooth-L1 Loss
    loss = K.switch(tf.size(target_bbox) > 0,
                    smooth_l1_loss(y_true=target_bbox, y_pred=pred_bbox),
                    tf.constant(0.0))
    loss = K.mean(loss)
    return loss 
Example #26
Source File: pixel_shuffler.py    From df with Mozilla Public License 2.0 5 votes vote down vote up
def call(self, inputs):

        input_shape = K.int_shape(inputs)
        if len(input_shape) != 4:
            raise ValueError('Inputs should have rank ' +
                             str(4) +
                             '; Received input shape:', str(input_shape))

        if self.data_format == 'channels_first':
            batch_size, c, h, w = input_shape
            if batch_size is None:
                batch_size = -1
            rh, rw = self.size
            oh, ow = h * rh, w * rw
            oc = c // (rh * rw)

            out = K.reshape(inputs, (batch_size, rh, rw, oc, h, w))
            out = K.permute_dimensions(out, (0, 3, 4, 1, 5, 2))
            out = K.reshape(out, (batch_size, oc, oh, ow))
            return out

        elif self.data_format == 'channels_last':
            batch_size, h, w, c = input_shape
            if batch_size is None:
                batch_size = -1
            rh, rw = self.size
            oh, ow = h * rh, w * rw
            oc = c // (rh * rw)

            out = K.reshape(inputs, (batch_size, h, w, rh, rw, oc))
            out = K.permute_dimensions(out, (0, 1, 3, 2, 4, 5))
            out = K.reshape(out, (batch_size, oh, ow, oc))
            return out 
Example #27
Source File: exampleTrainer.py    From df with Mozilla Public License 2.0 5 votes vote down vote up
def call(self, inputs):

        input_shape = K.int_shape(inputs)
        if len(input_shape) != 4:
            raise ValueError('Inputs should have rank ' +
                             str(4) +
                             '; Received input shape:', str(input_shape))

        if self.data_format == 'channels_first':
            batch_size, c, h, w = input_shape
            if batch_size is None:
                batch_size = -1
            rh, rw = self.size
            oh, ow = h * rh, w * rw
            oc = c // (rh * rw)

            out = K.reshape(inputs, (batch_size, rh, rw, oc, h, w))
            out = K.permute_dimensions(out, (0, 3, 4, 1, 5, 2))
            out = K.reshape(out, (batch_size, oc, oh, ow))
            return out

        elif self.data_format == 'channels_last':
            batch_size, h, w, c = input_shape
            if batch_size is None:
                batch_size = -1
            rh, rw = self.size
            oh, ow = h * rh, w * rw
            oc = c // (rh * rw)

            out = K.reshape(inputs, (batch_size, h, w, rh, rw, oc))
            out = K.permute_dimensions(out, (0, 1, 3, 2, 4, 5))
            out = K.reshape(out, (batch_size, oh, ow, oc))
            return out 
Example #28
Source File: classifiers.py    From AIX360 with Apache License 2.0 5 votes vote down vote up
def __init__(self, model, input_layer=0, output_layer=0):

        """Initialize KerasClassifier.

        Args:
            model: a trained keras classifier model.
        """

        import keras.backend as k

        super(KerasClassifier, self).__init__()

        self._model = model

        if hasattr(model, 'inputs'):
            self._input = model.inputs[input_layer]
        else:
            self._input = model.input

        if hasattr(model, 'outputs'):
            self._output = model.outputs[output_layer]
        else:
            self._output = model.output

        _, self._nb_classes = k.int_shape(self._output)
        self._input_shape   = k.int_shape(self._input)[1:] 
Example #29
Source File: visualizer.py    From backdoor with MIT License 5 votes vote down vote up
def reset_opt(self):

        K.set_value(self.opt.iterations, 0)
        for w in self.opt.weights:
            K.set_value(w, np.zeros(K.int_shape(w)))

        pass 
Example #30
Source File: model.py    From PanopticSegmentation with MIT License 5 votes vote down vote up
def mrcnn_bbox_loss_graph(target_bbox, target_class_ids, pred_bbox):
    """Loss for Mask R-CNN bounding box refinement.

    target_bbox: [batch, num_rois, (dy, dx, log(dh), log(dw))]
    target_class_ids: [batch, num_rois]. Integer class IDs.
    pred_bbox: [batch, num_rois, num_classes, (dy, dx, log(dh), log(dw))]
    """
    # Reshape to merge batch and roi dimensions for simplicity.
    target_class_ids = K.reshape(target_class_ids, (-1,))
    target_bbox = K.reshape(target_bbox, (-1, 4))
    pred_bbox = K.reshape(pred_bbox, (-1, K.int_shape(pred_bbox)[2], 4))

    # Only positive ROIs contribute to the loss. And only
    # the right class_id of each ROI. Get their indices.
    positive_roi_ix = tf.where(target_class_ids > 0)[:, 0]
    positive_roi_class_ids = tf.cast(
        tf.gather(target_class_ids, positive_roi_ix), tf.int64)
    indices = tf.stack([positive_roi_ix, positive_roi_class_ids], axis=1)

    # Gather the deltas (predicted and true) that contribute to loss
    target_bbox = tf.gather(target_bbox, positive_roi_ix)
    pred_bbox = tf.gather_nd(pred_bbox, indices)

    # Smooth-L1 Loss
    loss = K.switch(tf.size(target_bbox) > 0,
                    smooth_l1_loss(y_true=target_bbox, y_pred=pred_bbox),
                    tf.constant(0.0))
    loss = K.mean(loss)
    return loss