当前位置: 首页>>代码示例>>Python>>正文


Python layers.Conv1D方法代码示例

本文整理汇总了Python中tensorflow.keras.layers.Conv1D方法的典型用法代码示例。如果您正苦于以下问题:Python layers.Conv1D方法的具体用法?Python layers.Conv1D怎么用?Python layers.Conv1D使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在tensorflow.keras.layers的用法示例。


在下文中一共展示了layers.Conv1D方法的6个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: _create_encoder

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import Conv1D [as 别名]
def _create_encoder(self, n_layers, dropout):
    """Create the encoder as a tf.keras.Model."""
    input = self._create_features()
    gather_indices = Input(shape=(2,), dtype=tf.int32)
    prev_layer = input
    for i in range(len(self._filter_sizes)):
      filter_size = self._filter_sizes[i]
      kernel_size = self._kernel_sizes[i]
      if dropout > 0.0:
        prev_layer = Dropout(rate=dropout)(prev_layer)
      prev_layer = Conv1D(
          filters=filter_size, kernel_size=kernel_size,
          activation=tf.nn.relu)(prev_layer)
    prev_layer = Flatten()(prev_layer)
    prev_layer = Dense(
        self._decoder_dimension, activation=tf.nn.relu)(prev_layer)
    prev_layer = BatchNormalization()(prev_layer)
    return tf.keras.Model(inputs=[input, gather_indices], outputs=prev_layer) 
开发者ID:deepchem,项目名称:deepchem,代码行数:20,代码来源:seqtoseq.py

示例2: __init__

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import Conv1D [as 别名]
def __init__(self,
                 n_symbols: int,  # This argument is required!
                 filters: int = 32  # There's no way to change this
                                    # from the commandline - see `my_simple_model_with_hparams.py`
                 ) -> None:
        super().__init__(n_symbols)

        self.input_embedding = Embedding(n_symbols, 10)
        self.conv1d = Conv1D(filters=filters, kernel_size=7, strides=1, padding='same') 
开发者ID:songlab-cal,项目名称:tape-neurips2019,代码行数:11,代码来源:simple_model.py

示例3: define_model

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import Conv1D [as 别名]
def define_model(self):

         inputs = tf.keras.Input(shape=(n_inputs, 1), name='input')

         # 64 filters, 10 kernel size
         x = Conv1D(64, 10, activation='relu')(inputs)
         x = MaxPool1D()(x)
         x = BatchNormalization()(x)

         x = Conv1D(128, 10, activation='relu')(x)
         x = MaxPool1D()(x)
         x = BatchNormalization()(x)

         x = Conv1D(128, 10, activation='relu')(x)
         x = MaxPool1D()(x)
         x = BatchNormalization()(x)

         x = Conv1D(256, 10, activation='relu')(x)
         x = MaxPool1D()(x)
         x = BatchNormalization()(x)

         x = Flatten()(x)
         x = Dense(1024, activation='relu', name='dense_1')(x)
         x = BatchNormalization()(x)
         x = Dropout(dropout)(x)

         x = Dense(2048, activation='relu', name='dense_2')(x)
         x = BatchNormalization()(x)
         x = Dropout(dropout)(x)

         outputs = Dense(n_classes, activation='softmax', name='predictions')(x)

         self.cnn_model = tf.keras.Model(inputs=inputs, outputs=outputs)
         optimizer = tf.keras.optimizers.Adam(lr=learning_rate)
         accuracy = CategoricalAccuracy()
         self.cnn_model.compile(optimizer=optimizer, loss='categorical_crossentropy',
                                metrics=[accuracy]) 
开发者ID:hedrox,项目名称:ecg-classification,代码行数:39,代码来源:cnn_tf2.py

示例4: __init__

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import Conv1D [as 别名]
def __init__(self,
                 filters: int,
                 kernel_size: int,
                 dilation_rate: int,
                 dropout_rate: float,
                 activation: str,
                 **kwargs):
        super(ResidualBlock, self).__init__(**kwargs)

        self.filters = filters

        self.causal_conv_1 = layers.Conv1D(filters=self.filters,
                                           kernel_size=kernel_size,
                                           dilation_rate=dilation_rate,
                                           padding='causal')
        self.weight_norm_1 = layers.LayerNormalization()
        self.dropout_1 = layers.SpatialDropout1D(rate=dropout_rate)
        self.activation_1 = layers.Activation(activation)

        self.causal_conv_2 = layers.Conv1D(filters=self.filters,
                                           kernel_size=kernel_size,
                                           dilation_rate=dilation_rate,
                                           padding='causal')
        self.weight_norm_2 = layers.LayerNormalization()
        self.dropout_2 = layers.SpatialDropout1D(rate=dropout_rate)
        self.activation_2 = layers.Activation(activation)

        self.activation_3 = layers.Activation(activation) 
开发者ID:1044197988,项目名称:TF.Keras-Commonly-used-models,代码行数:30,代码来源:tcn.py

示例5: build

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import Conv1D [as 别名]
def build(self, input_shape):
        in_channels = input_shape[-1]
        if in_channels == self.filters:
            self.skip_conv = None
        else:
            self.skip_conv = layers.Conv1D(filters=self.filters,
                                           kernel_size=1)

        super(ResidualBlock, self).build(input_shape) 
开发者ID:1044197988,项目名称:TF.Keras-Commonly-used-models,代码行数:11,代码来源:tcn.py

示例6: _build_graph

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import Conv1D [as 别名]
def _build_graph(self):
    """Build the model."""
    smiles_seqs = Input(dtype=tf.int32, shape=(self.max_seq_len,), name='Input')
    rnn_input = tf.keras.layers.Embedding(
        input_dim=len(self.char_to_idx),
        output_dim=self.embedding_dim)(smiles_seqs)

    if self.use_conv:
      rnn_input = Conv1D(
          filters=self.filters,
          kernel_size=self.kernel_size,
          strides=self.strides,
          activation=tf.nn.relu,
          name='Conv1D')(rnn_input)

    rnn_embeddings = rnn_input
    for idx, rnn_type in enumerate(self.rnn_types[:-1]):
      rnn_layer = RNN_DICT[rnn_type]
      layer = rnn_layer(units=self.rnn_sizes[idx], return_sequences=True)
      if self.use_bidir:
        layer = Bidirectional(layer)

      rnn_embeddings = layer(rnn_embeddings)

    # Last layer sequences not returned.
    layer = RNN_DICT[self.rnn_types[-1]](units=self.rnn_sizes[-1])
    if self.use_bidir:
      layer = Bidirectional(layer)
    rnn_embeddings = layer(rnn_embeddings)

    if self.mode == "classification":
      logits = Dense(self.n_tasks * self.n_classes)(rnn_embeddings)
      logits = Reshape((self.n_tasks, self.n_classes))(logits)
      if self.n_classes == 2:
        output = Activation(activation='sigmoid')(logits)
        loss = SigmoidCrossEntropy()
      else:
        output = Softmax()(logits)
        loss = SoftmaxCrossEntropy()
      outputs = [output, logits]
      output_types = ['prediction', 'loss']

    else:
      output = Dense(self.n_tasks * 1, name='Dense')(rnn_embeddings)
      output = Reshape((self.n_tasks, 1), name='Reshape')(output)
      outputs = [output]
      output_types = ['prediction']
      loss = L2Loss()

    model = tf.keras.Model(inputs=[smiles_seqs], outputs=outputs)
    return model, loss, output_types 
开发者ID:deepchem,项目名称:deepchem,代码行数:53,代码来源:chemnet_models.py


注:本文中的tensorflow.keras.layers.Conv1D方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。