我们从Python开源项目中，提取了以下7个代码示例，用于说明如何使用keras.initializers.RandomUniform()。
def build(self, input_shape): assert len(input_shape) >= 2 input_dim = input_shape[1] if self.H == 'Glorot': self.H = np.float32(np.sqrt(1.5 / (input_dim + self.units))) #print('Glorot H: {}'.format(self.H)) if self.kernel_lr_multiplier == 'Glorot': self.kernel_lr_multiplier = np.float32(1. / np.sqrt(1.5 / (input_dim + self.units))) #print('Glorot learning rate multiplier: {}'.format(self.kernel_lr_multiplier)) self.kernel_constraint = Clip(-self.H, self.H) self.kernel_initializer = initializers.RandomUniform(-self.H, self.H) self.kernel = self.add_weight(shape=(input_dim, self.units), initializer=self.kernel_initializer, name='kernel', regularizer=self.kernel_regularizer, constraint=self.kernel_constraint) if self.use_bias: self.lr_multipliers = [self.kernel_lr_multiplier, self.bias_lr_multiplier] self.bias = self.add_weight(shape=(self.output_dim,), initializer=self.bias_initializer, name='bias', regularizer=self.bias_regularizer, constraint=self.bias_constraint) else: self.lr_multipliers = [self.kernel_lr_multiplier] self.bias = None self.input_spec = InputSpec(min_ndim=2, axes={-1: input_dim}) self.built = True
def build(self, input_shape): assert len(input_shape) >= 2 input_dim = input_shape[1] if self.H == 'Glorot': self.H = np.float32(np.sqrt(1.5 / (input_dim + self.units))) #print('Glorot H: {}'.format(self.H)) if self.kernel_lr_multiplier == 'Glorot': self.kernel_lr_multiplier = np.float32(1. / np.sqrt(1.5 / (input_dim + self.units))) #print('Glorot learning rate multiplier: {}'.format(self.lr_multiplier)) self.kernel_constraint = Clip(-self.H, self.H) self.kernel_initializer = initializers.RandomUniform(-self.H, self.H) self.kernel = self.add_weight(shape=(input_dim, self.units), initializer=self.kernel_initializer, name='kernel', regularizer=self.kernel_regularizer, constraint=self.kernel_constraint) if self.use_bias: self.lr_multipliers = [self.kernel_lr_multiplier, self.bias_lr_multiplier] self.bias = self.add_weight(shape=(self.output_dim,), initializer=self.bias_initializer, name='bias', regularizer=self.bias_regularizer, constraint=self.bias_constraint) else: self.lr_multipliers = [self.kernel_lr_multiplier] self.bias = None self.built = True
def build(self, input_shape): 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] kernel_shape = self.kernel_size + (input_dim, self.filters) base = self.kernel_size[0] * self.kernel_size[1] if self.H == 'Glorot': nb_input = int(input_dim * base) nb_output = int(self.filters * base) self.H = np.float32(np.sqrt(1.5 / (nb_input + nb_output))) #print('Glorot H: {}'.format(self.H)) if self.kernel_lr_multiplier == 'Glorot': nb_input = int(input_dim * base) nb_output = int(self.filters * base) self.kernel_lr_multiplier = np.float32(1. / np.sqrt(1.5/ (nb_input + nb_output))) #print('Glorot learning rate multiplier: {}'.format(self.lr_multiplier)) self.kernel_constraint = Clip(-self.H, self.H) self.kernel_initializer = initializers.RandomUniform(-self.H, self.H) self.kernel = self.add_weight(shape=kernel_shape, initializer=self.kernel_initializer, name='kernel', regularizer=self.kernel_regularizer, constraint=self.kernel_constraint) if self.use_bias: self.lr_multipliers = [self.kernel_lr_multiplier, self.bias_lr_multiplier] self.bias = self.add_weight((self.output_dim,), initializer=self.bias_initializers, name='bias', regularizer=self.bias_regularizer, constraint=self.bias_constraint) else: self.lr_multipliers = [self.kernel_lr_multiplier] self.bias = None # Set input spec. self.input_spec = InputSpec(ndim=4, axes={channel_axis: input_dim}) self.built = True
def __init__(self, learning_rate=None, vocab_size=None, embedding_size=None, rnn_output_size=None, dropout_rate=None, bidirectional_rnn=None, rnn_type=None, rnn_layers=None, l1_reg=None, l2_reg=None, initializer=None, word_vector_init=None): """ If an arg is None, it will get its value from config.active_config. """ self._learning_rate = learning_rate or active_config().learning_rate self._vocab_size = vocab_size or active_config().vocab_size self._embedding_size = embedding_size or active_config().embedding_size self._rnn_output_size = (rnn_output_size or active_config().rnn_output_size) self._dropout_rate = dropout_rate or active_config().dropout_rate self._rnn_type = rnn_type or active_config().rnn_type self._rnn_layers = rnn_layers or active_config().rnn_layers self._word_vector_init = (word_vector_init or active_config().word_vector_init) self._initializer = initializer or active_config().initializer if self._initializer == 'vinyals_uniform': self._initializer = RandomUniform(-0.08, 0.08) if bidirectional_rnn is None: self._bidirectional_rnn = active_config().bidirectional_rnn else: self._bidirectional_rnn = bidirectional_rnn l1_reg = l1_reg or active_config().l1_reg l2_reg = l2_reg or active_config().l2_reg self._regularizer = l1_l2(l1_reg, l2_reg) self._keras_model = None if self._vocab_size is None: raise ValueError('config.active_config().vocab_size cannot be ' 'None! You should check your config or you can ' 'explicitly pass the vocab_size argument.') if self._rnn_type not in ('lstm', 'gru'): raise ValueError('rnn_type must be either "lstm" or "gru"!') if self._rnn_layers < 1: raise ValueError('rnn_layers must be >= 1!') if self._word_vector_init is not None and self._embedding_size != 300: raise ValueError('If word_vector_init is not None, embedding_size ' 'must be 300')
def to_embedding(self, vector_dim=None, learn_difference=False, name=None, embeddings_initializer='he_normal'): from keras.layers import Embedding W = None if self.W is not None: W = np.zeros(( self.size + len(self._special_tokens), self.W.shape[1] )) W[len(self._special_tokens):, :] = self.W W = [W] vector_dim = self.W.shape[1] else: if vector_dim is None: ValueError('If container has no matrix W defined, vector ' 'dimension for embedding must be explicitly ' 'specified.') emb = Embedding( input_dim=self.size + len(self._special_tokens), output_dim=vector_dim, weights=W, mask_zero=True, name=name, embeddings_initializer=embeddings_initializer ) if learn_difference: if W is None: logger.warning('Learning a difference on top of non-pretrained ' 'word vectors is not recommended') from keras.models import Model from keras.initializers import RandomUniform from keras.layers import Input, add emb.trainable = False delta_initializer = RandomUniform(minval=-0.005, maxval=0.005) if name is None: name = emb.name delta = Embedding( input_dim=self.size + len(self._special_tokens), output_dim=vector_dim, embeddings_initializer=delta_initializer, mask_zero=True, name=name + '/delta_correction' ) x = Input((None, ), dtype='int32', name=name + '/input') e = add([emb(x), delta(x)], name=name + '/addition') emb = Model(x, e, name='shifted_emb/' + name) return emb
