Python backend.batch_dot方法代码示例

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def call(self, inputs, **kwargs):
        # (batch_size, 1, input_num_capsule, input_dim_capsule)
        expand_inputs = K.expand_dims(inputs, axis=1)
        # (batch_size, num_capsule, input_num_capsule, input_dim_capsule)
        expand_inputs = K.tile(expand_inputs, (1, self.num_capsule, 1, 1))
        # (batch_size, num_capsule, input_num_capsule, dim_capsule)
        u_hat = K.map_fn(lambda x: K.batch_dot(x, self.W, axes=[2, 3]), expand_inputs)

        if self.num_routing <= 0:
            self.num_routing = 3
        # (batch_size, num_capsule, input_num_capsule)
        b = K.zeros((K.shape(u_hat)[0], self.num_capsule, self.input_num_capsule))
        for i in xrange(self.num_routing):
            # (batch_size, num_capsule, input_num_capsule)
            c = softmax(b, axis=1)
            # (batch_size, num_capsule, dim_capsule)
            s = K.batch_dot(c, u_hat, axes=[2, 2])
            squashed_s = squash(s)
            if i < self.num_routing - 1:
                # (batch_size, num_capsule, input_num_capsule)
                b += K.batch_dot(squashed_s, u_hat, axes=[2, 3])
        return squashed_s 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def call(self , x, mask=None):
        
        e1=x[0].T
        e2=x[1].T
        
        batch_size = K.shape(x[0])[0]
        sim = []
        V_out = K.dot(self.V, K.concatenate([e1,e2],axis=0))     

        for i in range(self.k): 
            temp = K.batch_dot(K.dot(e1.T,self.W[i,:,:]),e2.T,axes=1)
            sim.append(temp)
        sim=K.reshape(sim,(self.k,batch_size))

        tensor_bi_product = self.activation(V_out+sim)
        tensor_bi_product = K.dot(self.U.T, tensor_bi_product).T

        return tensor_bi_product 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def call(self, inputs, training=None):
        inputs_expand = K.expand_dims(inputs, 1)
        
        inputs_tiled = K.tile(inputs_expand, [1, self.num_capsule, 1, 1])
        
        if(self.channels!=0):
            W2 = K.repeat_elements(self.W,int(self.input_num_capsule/self.channels),1)
        else:
            W2 = self.W
            
        inputs_hat = K.map_fn(lambda x: K.batch_dot(x, W2, [2, 3]) , elems=inputs_tiled)

        b = tf.zeros(shape=[K.shape(inputs_hat)[0], self.num_capsule, self.input_num_capsule])

        assert self.routings > 0, 'The routings should be > 0.'
        for i in range(self.routings):

            c = tf.nn.softmax(b, dim=1)
            outputs = squash(K.batch_dot(c, inputs_hat, [2, 2])+ self.B)

            if i < self.routings - 1:
                b += K.batch_dot(outputs, inputs_hat, [2, 3])

        return outputs 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def call(self, u_vecs):
        if self.share_weights:
            u_hat_vecs = K.conv1d(u_vecs, self.W)
        else:
            u_hat_vecs = K.local_conv1d(u_vecs, self.W, [1], [1])

        batch_size = K.shape(u_vecs)[0]
        input_num_capsule = K.shape(u_vecs)[1]
        u_hat_vecs = K.reshape(u_hat_vecs, (batch_size, input_num_capsule,
                                            self.num_capsule, self.dim_capsule))
        u_hat_vecs = K.permute_dimensions(u_hat_vecs, (0, 2, 1, 3))

        b = K.zeros_like(u_hat_vecs[:, :, :, 0])  # shape = [None, num_capsule, input_num_capsule]
        for i in range(self.routings):
            b = K.permute_dimensions(b, (0, 2, 1))  # shape = [None, input_num_capsule, num_capsule]
            c = K.softmax(b)
            c = K.permute_dimensions(c, (0, 2, 1))
            b = K.permute_dimensions(b, (0, 2, 1))
            outputs = self.activation(K.batch_dot(c, u_hat_vecs, [2, 2]))
            if i < self.routings - 1:
                b = K.batch_dot(outputs, u_hat_vecs, [2, 3])

        return outputs 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def routing(u_hat_vecs, beta_a, iterations, output_capsule_num, i_activations):
    b = keras.backend.zeros_like(u_hat_vecs[:,:,:,0])
    if i_activations is not None:
        i_activations = i_activations[...,tf.newaxis]
    for i in range(iterations):
        if False:
            leak = tf.zeros_like(b, optimize=True)
            leak = tf.reduce_sum(leak, axis=1, keep_dims=True)
            leaky_logits = tf.concat([leak, b], axis=1)
            leaky_routing = tf.nn.softmax(leaky_logits, dim=1)
            c = tf.split(leaky_routing, [1, output_capsule_num], axis=1)[1]
        else:
            c = softmax(b, 1)
#        if i_activations is not None:
#            tf.transpose(tf.transpose(c, perm=[0,2,1]) * i_activations, perm=[0,2,1])
        outputs = squash_v1(K.batch_dot(c, u_hat_vecs, [2, 2]))
        if i < iterations - 1:
            b = b + K.batch_dot(outputs, u_hat_vecs, [2, 3])
    poses = outputs
    activations = K.sqrt(K.sum(K.square(poses), 2))
    return poses, activations 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def call(self, inputs, mask=None, **kwargs):
        if isinstance(inputs, list):
            query, key, value = inputs
        else:
            query = key = value = inputs
        if isinstance(mask, list):
            mask = mask[1]
        feature_dim = K.shape(query)[-1]
        e = K.batch_dot(query, key, axes=2) / K.sqrt(K.cast(feature_dim, dtype=K.floatx()))
        e = K.exp(e - K.max(e, axis=-1, keepdims=True))
        if self.history_only:
            query_len, key_len = K.shape(query)[1], K.shape(key)[1]
            indices = K.tile(K.expand_dims(K.arange(key_len), axis=0), [query_len, 1])
            upper = K.expand_dims(K.arange(key_len), axis=-1)
            e *= K.expand_dims(K.cast(indices <= upper, K.floatx()), axis=0)
        if mask is not None:
            e *= K.cast(K.expand_dims(mask, axis=-2), K.floatx())
        a = e / (K.sum(e, axis=-1, keepdims=True) + K.epsilon())
        v = K.batch_dot(a, value)
        if self.return_attention:
            return [v, a]
        return v 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def call(self, u_vecs):
        if self.share_weights:
            u_hat_vecs = K.conv1d(u_vecs, self.W)
        else:
            u_hat_vecs = K.local_conv1d(u_vecs, self.W, [1], [1])

        batch_size = K.shape(u_vecs)[0]
        input_num_capsule = K.shape(u_vecs)[1]
        u_hat_vecs = K.reshape(u_hat_vecs, (batch_size, input_num_capsule,
                                            self.num_capsule, self.dim_capsule))
        u_hat_vecs = K.permute_dimensions(u_hat_vecs, (0, 2, 1, 3))
        # final u_hat_vecs.shape = [None, num_capsule, input_num_capsule, dim_capsule]

        b = K.zeros_like(u_hat_vecs[:, :, :, 0])  # shape = [None, num_capsule, input_num_capsule]
        outputs = None
        for i in range(self.routings):
            b = K.permute_dimensions(b, (0, 2, 1))  # shape = [None, input_num_capsule, num_capsule]
            c = K.softmax(b)
            c = K.permute_dimensions(c, (0, 2, 1))
            b = K.permute_dimensions(b, (0, 2, 1))
            outputs = self.activation(K.batch_dot(c, u_hat_vecs, [2, 2]))
            if i < self.routings - 1:
                b = K.batch_dot(outputs, u_hat_vecs, [2, 3])

        return outputs 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def _get_weight_vector(self, M, w_tm1, k, beta, g, s, gamma):
#        M = tf.Print(M, [M, w_tm1, k], message='get weights beg1: ')
#        M = tf.Print(M, [beta, g, s, gamma], message='get weights beg2: ')
        # Content adressing, see Chapter 3.3.1:
        num = beta * _cosine_distance(M, k)
        w_c  = K.softmax(num) # It turns out that equation (5) is just softmax.
        # Location adressing, see Chapter 3.3.2:
        # Equation 7:
        w_g = (g * w_c) + (1-g)*w_tm1
        # C_s is the circular convolution
        #C_w = K.sum((self.C[None, :, :, :] * w_g[:, None, None, :]),axis=3)
        # Equation 8:
        # TODO: Explain
        C_s = K.sum(K.repeat_elements(self.C[None, :, :, :], self.batch_size, axis=0) * s[:,:,None,None], axis=1)
        w_tilda = K.batch_dot(C_s, w_g)
        # Equation 9:
        w_out = _renorm(w_tilda ** gamma)

        return w_out 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def test_linear_operations(self):
        check_two_tensor_operation('dot', (4, 2), (2, 4), BACKENDS)
        check_two_tensor_operation('dot', (4, 2), (5, 2, 3), BACKENDS)

        check_two_tensor_operation('batch_dot', (4, 2, 3), (4, 5, 3),
                                   BACKENDS, cntk_two_dynamicity=True, axes=(2, 2))
        check_two_tensor_operation('batch_dot', (4, 2, 3), (4, 3),
                                   BACKENDS, cntk_two_dynamicity=True, axes=(2, 1))
        check_two_tensor_operation('batch_dot', (4, 2), (4, 2, 3),
                                   BACKENDS, cntk_two_dynamicity=True, axes=(1, 1))
        check_two_tensor_operation('batch_dot', (32, 20), (32, 20),
                                   BACKENDS, cntk_two_dynamicity=True, axes=1)
        check_two_tensor_operation('batch_dot', (32, 20), (32, 20),
                                   BACKENDS, cntk_two_dynamicity=True, axes=(1, 1))

        check_single_tensor_operation('transpose', (4, 2), BACKENDS)
        check_single_tensor_operation('reverse', (4, 3, 2), BACKENDS, axes=1)
        check_single_tensor_operation('reverse', (4, 3, 2), [KTH, KTF], axes=(1, 2)) 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def call(self, x, mask=None):
        uit = K.tanh(K.dot(x, self.Ws1))
        ait = K.dot(uit, self.Ws2)
        ait = K.permute_dimensions(ait, (0, 2, 1))
        A = K.softmax(ait, axis=1)
        M = K.batch_dot(A, x)
        if self.punish:
            A_T = K.permute_dimensions(A, (0, 2, 1))
            tile_eye = K.tile(K.eye(self.weight_ws2), [self.batch_size, 1])
            tile_eye = K.reshape(
                tile_eye, shape=[-1, self.weight_ws2, self.weight_ws2])
            AA_T = K.batch_dot(A, A_T) - tile_eye
            P = K.l2_normalize(AA_T, axis=(1, 2))
            return M, P
        else:
            return M 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def call(self, x, mask=None):
        q, k, v = x
        d_k = q.shape.as_list()[2]

        # in pure tensorflow:
        # weights = tf.matmul(x_batch, tf.transpose(y_batch, perm=[0, 2, 1]))
        # normalized_weights = tf.nn.softmax(weights/scaling)
        # output = tf.matmul(normalized_weights, x_batch)
        
        weights = K.batch_dot(q,  k, axes=[2, 2])

        if mask is not None:
            # add mask weights
            if isinstance(mask, (list, tuple)):
                if len(mask) > 0:
                    raise ValueError("mask can only be a Tensor or a list of length 1 containing a tensor.")

                mask = mask[0]

            weights += -1e10*(1-mask)

        normalized_weights = K.softmax(weights / np.sqrt(d_k))
        output = K.batch_dot(normalized_weights, v)
        
        if self._return_attention:
            return [output, normalized_weights]
        else:
            return output 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def _additive_similarity(self, source, query):
        concatenation = K.concatenate([source, query], axis=2)
        nonlinearity = K.tanh(K.dot(concatenation, self._weights["w_a"]))
        
        # tile the weight vector (1, 1, dim) for each time step and each element of the batch -> (bs, T, dim)
        source_shape = K.shape(source)
        vaeff = K.tile(K.expand_dims(self._weights["v_a"], 0), [source_shape[0], source_shape[1], 1])

        similarity = K.batch_dot(K.permute_dimensions(vaeff, [0, 2, 1]), nonlinearity, axes=[1, 2])
        
        return similarity 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def _multiplicative_similarity(self, source, query):
        qp = K.dot(query, self._weights["w_a"])
        similarity = K.batch_dot(K.permute_dimensions(qp, [0, 2, 1]), source, axes=[1, 2])
        
        return similarity 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def _transform_trans(theta,input):
    batch1, step1, dim1 = input.shape
    input = K.reshape(input,(batch1,step1,dim1//3,3))
    input = K.reshape(input,(batch1*step1,dim1//3,3))
    input = K.permute_dimensions(input,[0,2,1])
    add = T.ones((batch1*step1,1,dim1//3))
    input= K.concatenate([input,add],axis=1)

    output = K.batch_dot(theta,input)
    output = K.permute_dimensions(output,[0,2,1])
    output = K.reshape(output,(output.shape[0],dim1))
    output = K.reshape(output,(batch1,step1,output.shape[1]))

    return output 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import batch_dot [as 别名]
def _fusion(theta):

    rotation_x = _rotation_x(theta)
    rotation_y = _rotation_y(theta)
    rotation_z = _rotation_z(theta)

    rot = K.batch_dot(rotation_z,rotation_y)
    rot = K.batch_dot(rot,rotation_x)

    return rot