Python keras.backend.conv3d() Examples

def call(self, inputs):
        input_shape = K.shape(inputs)
        if self.data_format == 'channels_first':
            channel_axis = 1
        else:
            channel_axis = -1
        if input_shape[channel_axis] is None:
            raise ValueError('The channel dimension of the inputs '
                             'should be defined. Found `None`.')
        input_dim = input_shape[channel_axis]
        ker_shape = self.kernel_size + (input_dim, self.filters)
        nb_kernels = ker_shape[-2] * ker_shape[-1]
        kernel_shape_4_norm = (np.prod(self.kernel_size), nb_kernels)
        reshaped_kernel = K.reshape(self.kernel, kernel_shape_4_norm)
        normalized_weight = K.l2_normalize(reshaped_kernel, axis=0, epsilon=self.epsilon)
        normalized_weight = K.reshape(self.gamma, (1, ker_shape[-2] * ker_shape[-1])) * normalized_weight
        shaped_kernel = K.reshape(normalized_weight, ker_shape)
        shaped_kernel._keras_shape = ker_shape
        
        convArgs = {"strides":       self.strides[0]       if self.rank == 1 else self.strides,
                    "padding":       self.padding,
                    "data_format":   self.data_format,
                    "dilation_rate": self.dilation_rate[0] if self.rank == 1 else self.dilation_rate}
        convFunc = {1: K.conv1d,
                    2: K.conv2d,
                    3: K.conv3d}[self.rank]
        output = convFunc(inputs, shaped_kernel, **convArgs)

        if self.use_bias:
            output = K.bias_add(
                output,
                self.bias,
                data_format=self.data_format
            )

        if self.activation is not None:
            output = self.activation(output)

        return output 

def call(self, inputs, training=None):
        def _l2normalize(v, eps=1e-12):
            return v / (K.sum(v ** 2) ** 0.5 + eps)
        def power_iteration(W, u):
            #Accroding the paper, we only need to do power iteration one time.
            _u = u
            _v = _l2normalize(K.dot(_u, K.transpose(W)))
            _u = _l2normalize(K.dot(_v, W))
            return _u, _v
        #Spectral Normalization
        W_shape = self.kernel.shape.as_list()
        #Flatten the Tensor
        W_reshaped = K.reshape(self.kernel, [-1, W_shape[-1]])
        _u, _v = power_iteration(W_reshaped, self.u)
        #Calculate Sigma
        sigma=K.dot(_v, W_reshaped)
        sigma=K.dot(sigma, K.transpose(_u))
        #normalize it
        W_bar = W_reshaped / sigma
        #reshape weight tensor
        if training in {0, False}:
            W_bar = K.reshape(W_bar, W_shape)
        else:
            with tf.control_dependencies([self.u.assign(_u)]):
                W_bar = K.reshape(W_bar, W_shape)
                
        outputs = K.conv3d(
                inputs,
                W_bar,
                strides=self.strides,
                padding=self.padding,
                data_format=self.data_format,
                dilation_rate=self.dilation_rate)
        if self.use_bias:
            outputs = K.bias_add(
                outputs,
                self.bias,
                data_format=self.data_format)
        if self.activation is not None:
            return self.activation(outputs)
        return outputs 

def call(self, input_tensor, training=None):

        input_transposed = tf.transpose(input_tensor, [0, 3, 4, 1, 2])
        input_shape = K.shape(input_transposed)
        input_tensor_reshaped = K.reshape(input_tensor, [input_shape[0], 1, self.input_num_capsule * self.input_num_atoms, self.input_height, self.input_width])

        input_tensor_reshaped.set_shape((None, 1, self.input_num_capsule * self.input_num_atoms, self.input_height, self.input_width))

        # conv = Conv3D(input_tensor_reshaped, self.W, (self.strides, self.strides),
        #                 padding=self.padding, data_format='channels_first')

        conv = K.conv3d(input_tensor_reshaped, self.W, strides=(self.input_num_atoms, self.strides, self.strides), padding=self.padding, data_format='channels_first')

        votes_shape = K.shape(conv)
        _, _, _, conv_height, conv_width = conv.get_shape()
        conv = tf.transpose(conv, [0, 2, 1, 3, 4])
        votes = K.reshape(conv, [input_shape[0], self.input_num_capsule, self.num_capsule, self.num_atoms, votes_shape[3], votes_shape[4]])
        votes.set_shape((None, self.input_num_capsule, self.num_capsule, self.num_atoms, conv_height.value, conv_width.value))

        logit_shape = K.stack([input_shape[0], self.input_num_capsule, self.num_capsule, votes_shape[3], votes_shape[4]])
        biases_replicated = K.tile(self.b, [1, 1, conv_height.value, conv_width.value])

        activations = update_routing(
            votes=votes,
            biases=biases_replicated,
            logit_shape=logit_shape,
            num_dims=6,
            input_dim=self.input_num_capsule,
            output_dim=self.num_capsule,
            num_routing=self.routings)

        a2 = tf.transpose(activations, [0, 3, 4, 1, 2])
        return a2 

def call(self, inputs):
        channel_axis = 1 if self.data_format == 'channels_first' else -1
        input_dim    = K.shape(inputs)[channel_axis] // 4
        index2 = self.filters*2
        index3 = self.filters*3
        if self.rank == 1:
            f_r   = self.kernel[:, :, :self.filters]
            f_i   = self.kernel[:, :, self.filters:index2]
            f_j   = self.kernel[:, :, index2:index3]
            f_k   = self.kernel[:, :, index3:]
        elif self.rank == 2:
            f_r   = self.kernel[:, :, :, :self.filters]
            f_i   = self.kernel[:, :, :, self.filters:index2]
            f_j   = self.kernel[:, :, :, index2:index3]
            f_k   = self.kernel[:, :, :, index3:]
        elif self.rank == 3:
            f_r   = self.kernel[:, :, :, :, :self.filters]
            f_i   = self.kernel[:, :, :, :, self.filters:index2]
            f_j   = self.kernel[:, :, :, :, index2:index3]
            f_k   = self.kernel[:, :, :, :, index3:]

        convArgs = {"strides":       self.strides[0]       if self.rank == 1 else self.strides,
                    "padding":       self.padding,
                    "data_format":   self.data_format,
                    "dilation_rate": self.dilation_rate[0] if self.rank == 1 else self.dilation_rate}
        convFunc = {1: K.conv1d,
                    2: K.conv2d,
                    3: K.conv3d}[self.rank]

                
        #
        # Performing quaternion convolution
        #
        
        f_r._keras_shape = self.kernel_shape
        f_i._keras_shape = self.kernel_shape
        f_j._keras_shape = self.kernel_shape
        f_k._keras_shape = self.kernel_shape

        cat_kernels_4_r = K.concatenate([f_r, -f_i, -f_j, -f_k], axis=-2)
        cat_kernels_4_i = K.concatenate([f_i, f_r, -f_k, f_j], axis=-2)
        cat_kernels_4_j = K.concatenate([f_j, f_k, f_r, -f_i], axis=-2)
        cat_kernels_4_k = K.concatenate([f_k, -f_j, f_i, f_r], axis=-2)
        cat_kernels_4_quaternion = K.concatenate([cat_kernels_4_r, cat_kernels_4_i, cat_kernels_4_j, cat_kernels_4_k], axis=-1)
        cat_kernels_4_quaternion._keras_shape = self.kernel_size + (4 * input_dim, 4 * self.filters)

        output = convFunc(inputs, cat_kernels_4_quaternion, **convArgs)

        if self.use_bias:
            output = K.bias_add(
                output,
                self.bias,
                data_format=self.data_format
            )
        if self.activation is not None:
            output = self.activation(output)

        return output 

def call(self, inputs, mask=None):
        # compute channels_firste candidate hidden state
         # Arguments
        '''
        x: Tensor or variable.
        kernel: kernel tensor.
        strides: strides tuple.
        padding: string, `"same"` or `"valid"`.
        data_format: string, `"channels_last"` or `"channels_first"`.
            Whether to use Theano or TensorFlow/CNTK data format
            for inputs/kernels/outputs.
        dilation_rate: tuple of 3 integers.
        '''
        transform = K.conv3d(
                inputs,
                self.kernel,
                strides=self.strides,
                padding=self.padding,
                data_format=self.data_format,
                dilation_rate=self.dilation_rate)

        if self.use_bias:
            transform = K.bias_add(
                transform,
                self.bias,
                data_format=self.data_format)

        if self.activation is not None:
            transform = self.activation(transform)

        transform_gate = K.conv3d(
                inputs,
                self.kernel_gate,
                strides=self.strides,
                padding=self.padding,
                data_format=self.data_format,
                dilation_rate=self.dilation_rate)

        if self.use_bias:
            transform = K.bias_add(
                transform,
                self.bias_gate,
                data_format=self.data_format)
        
        transform_gate = K.sigmoid(transform_gate)
       
        carry_gate = 1.0 - transform_gate

        return transform * transform_gate + inputs * carry_gate 

def call(self, inputs):
        if self.rank == 1:
            expert_outputs = K.conv1d(
                inputs,
                self.expert_kernel,
                strides=self.strides[0],
                padding=self.padding,
                data_format=self.data_format,
                dilation_rate=self.dilation_rate[0])
        if self.rank == 2:
            expert_outputs = K.conv2d(
                inputs,
                self.expert_kernel,
                strides=self.strides,
                padding=self.padding,
                data_format=self.data_format,
                dilation_rate=self.dilation_rate)
        if self.rank == 3:
            expert_outputs = K.conv3d(
                inputs,
                self.expert_kernel,
                strides=self.strides,
                padding=self.padding,
                data_format=self.data_format,
                dilation_rate=self.dilation_rate)

        expert_outputs = K.reshape(expert_outputs, (-1,) + self.o_shape[1:-1] + (self.n_filters, self.n_experts_per_filter))

        if self.use_expert_bias:
            expert_outputs = K.bias_add(
                expert_outputs,
                self.expert_bias,
                data_format=self.data_format)

        if self.expert_activation is not None:
            expert_outputs = self.expert_activation(expert_outputs)

        gating_outputs = tf.tensordot(inputs, self.gating_kernel, axes=self.rank+1) # samples x n_filters x n_experts_per_filter

        if self.use_gating_bias:
            gating_outputs = K.bias_add(
                gating_outputs,
                self.gating_bias,
                data_format=self.data_format)

        if self.gating_activation is not None:
            gating_outputs = self.gating_activation(gating_outputs)

        gating_outputs = K.reshape(gating_outputs, self.new_gating_outputs_shape)
        outputs = K.sum(expert_outputs * gating_outputs, axis=-1, keepdims=False)

        return outputs