我们从Python开源项目中，提取了以下10个代码示例，用于说明如何使用keras.backend.random_uniform_variable()。
def KerasCost(self,y_true, y_pred): #create a random subsampling of the target instances for the test set #This is rarely going to hit the last entry sample = K.cast(K.round(K.random_uniform_variable(shape=tuple([self.MMDTargetSampleSize]), low=0, high=self.MMDTargetTrainSize-1)),IntType) #this is a subset operation (not a very pretty way to do it) MMDTargetSampleTrain = K.gather(self.MMDTargetTrain,sample) #do the same for the validation set sample = K.cast(K.round(K.random_uniform_variable(shape=tuple([self.MMDTargetSampleSize]), low=0, high=self.MMDTargetValidationSize-1)),IntType) #and the subset operation MMDTargetSampleValidation = K.gather(self.MMDTargetValidation,sample) #create the sample based on whether we are in training or validation steps MMDtargetSample = K.in_train_phase(MMDTargetSampleTrain, MMDTargetSampleValidation) #return the MMD cost for this subset ret= self.cost(self.MMDLayer,MMDtargetSample) #pretty dumb but y_treu has to be in the cost for keras to not barf when cleaning up ret = ret + 0*K.sum(y_pred)+0*K.sum(y_true) return ret
def build(self, input_shape): if self.W is None: self.W = K.variable(np.identity(input_shape[0][2])) elif isinstance(self.W, np.ndarray): self.W = K.variable(self.W) else: raise RuntimeError() if self.b is None: self.b = K.random_uniform_variable((input_shape[0][2],), -0.05, 0.05) elif isinstance(self.b, np.ndarray): self.b = K.variable(self.b) else: raise RuntimeError() self.trainable_weights = [self.W, self.b]
def _get_initial_sense_priors(shape, rate_range=None, name=None): # This returns a Keras variable with the initial values all being 0.5. if rate_range is None: low, high = 0.01, 0.99 else: low, high = rate_range return K.random_uniform_variable(shape, low, high, name=name)
def create_full_matching_layer_f(self, input_dim_a, input_dim_b): """Create a full-matching layer of a model.""" inp_a = Input(shape=(input_dim_a, self.hidden_dim,)) inp_b = Input(shape=(input_dim_b, self.hidden_dim,)) W = [] for i in range(self.perspective_num): wi = K.random_uniform_variable((1, self.hidden_dim), -1.0, 1.0, seed=self.seed if self.seed is not None else 243) W.append(wi) val = np.concatenate((np.zeros((self.max_sequence_length-1,1)), np.ones((1,1))), axis=0) kcon = K.constant(value=val, dtype='float32') inp_b_perm = Lambda(lambda x: K.permute_dimensions(x, (0,2,1)))(inp_b) last_state = Lambda(lambda x: K.permute_dimensions(K.dot(x, kcon), (0,2,1)))(inp_b_perm) m = [] for i in range(self.perspective_num): outp_a = Lambda(lambda x: x * W[i])(inp_a) outp_last = Lambda(lambda x: x * W[i])(last_state) outp_a = Lambda(lambda x: K.l2_normalize(x, -1))(outp_a) outp_last = Lambda(lambda x: K.l2_normalize(x, -1))(outp_last) outp_last = Lambda(lambda x: K.permute_dimensions(x, (0,2,1)))(outp_last) outp = Lambda(lambda x: K.batch_dot(x[0], x[1], axes=[1, 2]))([outp_last, outp_a]) outp = Lambda(lambda x: K.permute_dimensions(x, (0,2,1)))(outp) m.append(outp) if self.perspective_num > 1: persp = Lambda(lambda x: K.concatenate(x, 2))(m) else: persp = m model = Model(inputs=[inp_a, inp_b], outputs=persp) return model
def create_full_matching_layer_b(self, input_dim_a, input_dim_b): """Create a full-matching layer of a model.""" inp_a = Input(shape=(input_dim_a, self.hidden_dim,)) inp_b = Input(shape=(input_dim_b, self.hidden_dim,)) W = [] for i in range(self.perspective_num): wi = K.random_uniform_variable((1, self.hidden_dim), -1.0, 1.0, seed=self.seed if self.seed is not None else 243) W.append(wi) val = np.concatenate((np.ones((1, 1)), np.zeros((self.max_sequence_length - 1, 1))), axis=0) kcon = K.constant(value=val, dtype='float32') inp_b_perm = Lambda(lambda x: K.permute_dimensions(x, (0, 2, 1)))(inp_b) last_state = Lambda(lambda x: K.permute_dimensions(K.dot(x, kcon), (0, 2, 1)))(inp_b_perm) m = [] for i in range(self.perspective_num): outp_a = Lambda(lambda x: x * W[i])(inp_a) outp_last = Lambda(lambda x: x * W[i])(last_state) outp_a = Lambda(lambda x: K.l2_normalize(x, -1))(outp_a) outp_last = Lambda(lambda x: K.l2_normalize(x, -1))(outp_last) outp_last = Lambda(lambda x: K.permute_dimensions(x, (0, 2, 1)))(outp_last) outp = Lambda(lambda x: K.batch_dot(x[0], x[1], axes=[1, 2]))([outp_last, outp_a]) outp = Lambda(lambda x: K.permute_dimensions(x, (0, 2, 1)))(outp) m.append(outp) if self.perspective_num > 1: persp = Lambda(lambda x: K.concatenate(x, 2))(m) else: persp = m model = Model(inputs=[inp_a, inp_b], outputs=persp) return model
def create_maxpool_matching_layer(self, input_dim_a, input_dim_b): """Create a maxpooling-matching layer of a model.""" inp_a = Input(shape=(input_dim_a, self.hidden_dim,)) inp_b = Input(shape=(input_dim_b, self.hidden_dim,)) W = [] for i in range(self.perspective_num): wi = K.random_uniform_variable((1, self.hidden_dim), -1.0, 1.0, seed=self.seed if self.seed is not None else 243) W.append(wi) m = [] for i in range(self.perspective_num): outp_a = Lambda(lambda x: x * W[i])(inp_a) outp_b = Lambda(lambda x: x * W[i])(inp_b) outp_a = Lambda(lambda x: K.l2_normalize(x, -1))(outp_a) outp_b = Lambda(lambda x: K.l2_normalize(x, -1))(outp_b) outp_b = Lambda(lambda x: K.permute_dimensions(x, (0,2,1)))(outp_b) outp = Lambda(lambda x: K.batch_dot(x[0], x[1], axes=[1, 2]))([outp_b, outp_a]) outp = Lambda(lambda x: K.permute_dimensions(x, (0,2,1)))(outp) outp = Lambda(lambda x: K.max(x, -1, keepdims=True))(outp) m.append(outp) if self.perspective_num > 1: persp = Lambda(lambda x: K.concatenate(x, 2))(m) else: persp = m model = Model(inputs=[inp_a, inp_b], outputs=persp) return model
def create_maxatt_matching_layer(self, input_dim_a, input_dim_b): """Create a max-attentive-matching layer of a model.""" inp_a = Input(shape=(input_dim_a, self.hidden_dim,)) inp_b = Input(shape=(input_dim_b, self.hidden_dim,)) W = [] for i in range(self.perspective_num): wi = K.random_uniform_variable((1, self.hidden_dim), -1.0, 1.0, seed=self.seed if self.seed is not None else 243) W.append(wi) outp_a = Lambda(lambda x: K.l2_normalize(x, -1))(inp_a) outp_b = Lambda(lambda x: K.l2_normalize(x, -1))(inp_b) outp_b = Lambda(lambda x: K.permute_dimensions(x, (0, 2, 1)))(outp_b) alpha = Lambda(lambda x: K.batch_dot(x[0], x[1], axes=[1, 2]))([outp_b, outp_a]) alpha = Lambda(lambda x: K.one_hot(K.argmax(x, 1), self.max_sequence_length))(alpha) hmax = Lambda(lambda x: K.batch_dot(x[0], x[1], axes=[1, 2]))([alpha, outp_b]) m = [] for i in range(self.perspective_num): outp_a = Lambda(lambda x: x * W[i])(inp_a) outp_hmax = Lambda(lambda x: x * W[i])(hmax) outp_a = Lambda(lambda x: K.l2_normalize(x, -1))(outp_a) outp_hmax = Lambda(lambda x: K.l2_normalize(x, -1))(outp_hmax) outp_hmax = Lambda(lambda x: K.permute_dimensions(x, (0, 2, 1)))(outp_hmax) outp = Lambda(lambda x: K.batch_dot(x[0], x[1], axes=[1, 2]))([outp_hmax, outp_a]) val = np.eye(self.max_sequence_length) kcon = K.constant(value=val, dtype='float32') outp = Lambda(lambda x: K.sum(x * kcon, -1, keepdims=True))(outp) m.append(outp) if self.perspective_num > 1: persp = Lambda(lambda x: K.concatenate(x, 2))(m) else: persp = m model = Model(inputs=[inp_a, inp_b], outputs=persp) return model
def create_att_matching_layer(self, input_dim_a, input_dim_b): """Create an attentive-matching layer of a model.""" inp_a = Input(shape=(input_dim_a, self.hidden_dim,)) inp_b = Input(shape=(input_dim_b, self.hidden_dim,)) w = [] for i in range(self.perspective_num): wi = K.random_uniform_variable((1, self.hidden_dim), -1.0, 1.0, seed=self.seed if self.seed is not None else 243) w.append(wi) outp_a = Lambda(lambda x: K.l2_normalize(x, -1))(inp_a) outp_b = Lambda(lambda x: K.l2_normalize(x, -1))(inp_b) outp_b = Lambda(lambda x: K.permute_dimensions(x, (0, 2, 1)))(outp_b) alpha = Lambda(lambda x: K.batch_dot(x[0], x[1], axes=[1, 2]))([outp_b, outp_a]) alpha = Lambda(lambda x: K.l2_normalize(x, 1))(alpha) hmean = Lambda(lambda x: K.batch_dot(x[0], x[1], axes=[1, 2]))([alpha, outp_b]) m = [] for i in range(self.perspective_num): outp_a = Lambda(lambda x: x * w[i])(inp_a) outp_hmean = Lambda(lambda x: x * w[i])(hmean) outp_a = Lambda(lambda x: K.l2_normalize(x, -1))(outp_a) outp_hmean = Lambda(lambda x: K.l2_normalize(x, -1))(outp_hmean) outp_hmean = Lambda(lambda x: K.permute_dimensions(x, (0, 2, 1)))(outp_hmean) outp = Lambda(lambda x: K.batch_dot(x[0], x[1], axes=[1, 2]))([outp_hmean, outp_a]) val = np.eye(self.max_sequence_length) kcon = K.constant(value=val, dtype='float32') outp = Lambda(lambda x: K.sum(x * kcon, -1, keepdims=True))(outp) m.append(outp) if self.perspective_num > 1: persp = Lambda(lambda x: K.concatenate(x, 2))(m) else: persp = m model = Model(inputs=[inp_a, inp_b], outputs=persp) return model
def get_coordinates(matrix_shape, input_channels, num_filters, scale=1.0): """ Return meshgrid coordinates. Flattened and stacked in columns. Parameters ---------- matrix_shape : list_like Shape of the output matrix scale : float Range of the coordinate representation (-scale, scale) Returns ------- coords : keras tensor """ # Generate coordinate data x = np.arange(matrix_shape[0]) - matrix_shape[0] // 2 y = np.arange(matrix_shape[1]) - matrix_shape[1] // 2 c = np.arange(input_channels) - input_channels // 2 f = np.arange(num_filters) - num_filters // 2 x = x / (x.max() + 1) y = y / (y.max() + 1) c = c / (c.max() + 1) f = f / (f.max() + 1) # to prevent division by zero x *= scale y *= scale c *= scale f *= scale # Generate coordinate data # the sequence in the meshgrid similar to output of generator F, C, X, Y = np.meshgrid(f, c, x, y) R = np.sqrt((X**2) + (Y**2) + (C**2) + (F**2)) total_items = np.prod(matrix_shape) * num_filters * input_channels # Flatten Y_r = Y.reshape(total_items) X_r = X.reshape(total_items) C_r = C.reshape(total_items) F_r = F.reshape(total_items) R_r = R.reshape(total_items) # Random variable Rand = K.random_uniform_variable(shape=(Y_r.shape[0], 1), low=0, high=1) coordinates = K.variable(value=np.vstack([X_r, Y_r, C_r, F_r, R_r]).T) # coordinates = K.concatenate([Rand, coordinates], axis=1) return coordinates
