当前位置: 首页>>代码示例>>Python>>正文


Python layers.conv2d方法代码示例

本文整理汇总了Python中tensorflow.contrib.slim.layers.conv2d方法的典型用法代码示例。如果您正苦于以下问题:Python layers.conv2d方法的具体用法?Python layers.conv2d怎么用?Python layers.conv2d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.contrib.slim.layers的用法示例。


在下文中一共展示了layers.conv2d方法的4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: basic_conv_lstm_cell

# 需要导入模块: from tensorflow.contrib.slim import layers [as 别名]
# 或者: from tensorflow.contrib.slim.layers import conv2d [as 别名]
def basic_conv_lstm_cell(inputs,
                         state,
                         num_channels,
                         filter_size=5,
                         forget_bias=1.0,
                         scope=None,
                         reuse=None):
  """Basic LSTM recurrent network cell, with 2D convolution connctions.

  We add forget_bias (default: 1) to the biases of the forget gate in order to
  reduce the scale of forgetting in the beginning of the training.

  It does not allow cell clipping, a projection layer, and does not
  use peep-hole connections: it is the basic baseline.

  Args:
    inputs: input Tensor, 4D, batch x height x width x channels.
    state: state Tensor, 4D, batch x height x width x channels.
    num_channels: the number of output channels in the layer.
    filter_size: the shape of the each convolution filter.
    forget_bias: the initial value of the forget biases.
    scope: Optional scope for variable_scope.
    reuse: whether or not the layer and the variables should be reused.

  Returns:
     a tuple of tensors representing output and the new state.
  """
  spatial_size = inputs.get_shape()[1:3]
  if state is None:
    state = init_state(inputs, list(spatial_size) + [2 * num_channels])
  with tf.variable_scope(scope,
                         'BasicConvLstmCell',
                         [inputs, state],
                         reuse=reuse):
    inputs.get_shape().assert_has_rank(4)
    state.get_shape().assert_has_rank(4)
    c, h = tf.split(axis=3, num_or_size_splits=2, value=state)
    inputs_h = tf.concat(axis=3, values=[inputs, h])
    # Parameters of gates are concatenated into one conv for efficiency.
    i_j_f_o = layers.conv2d(inputs_h,
                            4 * num_channels, [filter_size, filter_size],
                            stride=1,
                            activation_fn=None,
                            scope='Gates')

    # i = input_gate, j = new_input, f = forget_gate, o = output_gate
    i, j, f, o = tf.split(axis=3, num_or_size_splits=4, value=i_j_f_o)

    new_c = c * tf.sigmoid(f + forget_bias) + tf.sigmoid(i) * tf.tanh(j)
    new_h = tf.tanh(new_c) * tf.sigmoid(o)

    return new_h, tf.concat(axis=3, values=[new_c, new_h]) 
开发者ID:ringringyi,项目名称:DOTA_models,代码行数:54,代码来源:lstm_ops.py

示例2: basic_conv_lstm_cell

# 需要导入模块: from tensorflow.contrib.slim import layers [as 别名]
# 或者: from tensorflow.contrib.slim.layers import conv2d [as 别名]
def basic_conv_lstm_cell(inputs,
                         state,
                         num_channels,
                         filter_size=5,
                         forget_bias=1.0,
                         scope=None,
                         reuse=None,
                         ):
    """Basic LSTM recurrent network cell, with 2D convolution connctions.
    We add forget_bias (default: 1) to the biases of the forget gate in order to
    reduce the scale of forgetting in the beginning of the training.
    It does not allow cell clipping, a projection layer, and does not
    use peep-hole connections: it is the basic baseline.
    Args:
        inputs: input Tensor, 4D, batch x height x width x channels.
        state: state Tensor, 4D, batch x height x width x channels.
        num_channels: the number of output channels in the layer.
        filter_size: the shape of the each convolution filter.
        forget_bias: the initial value of the forget biases.
        scope: Optional scope for variable_scope.
        reuse: whether or not the layer and the variables should be reused.
    Returns:
        a tuple of tensors representing output and the new state.
    """
    if state is None:
        state = tf.zeros(inputs.get_shape().as_list()[:3] + [2 * num_channels], name='init_state')

    with tf.variable_scope(scope,
                           'BasicConvLstmCell',
                           [inputs, state],
                           reuse=reuse):

        inputs.get_shape().assert_has_rank(4)
        state.get_shape().assert_has_rank(4)
        c, h = tf.split(axis=3, num_or_size_splits=2, value=state)
        inputs_h = tf.concat(values=[inputs, h], axis=3)
        # Parameters of gates are concatenated into one conv for efficiency.
        i_j_f_o = layers.conv2d(inputs_h,
                                4 * num_channels, [filter_size, filter_size],
                                stride=1,
                                activation_fn=None,
                                scope='Gates',
                                )

        # i = input_gate, j = new_input, f = forget_gate, o = output_gate
        i, j, f, o = tf.split(value=i_j_f_o, num_or_size_splits=4, axis=3)

        new_c = c * tf.sigmoid(f + forget_bias) + tf.sigmoid(i) * tf.tanh(j)
        new_h = tf.tanh(new_c) * tf.sigmoid(o)

        return new_h, tf.concat(values=[new_c, new_h], axis=3) 
开发者ID:alexlee-gk,项目名称:video_prediction,代码行数:53,代码来源:sna_model.py

示例3: basic_conv_lstm_cell

# 需要导入模块: from tensorflow.contrib.slim import layers [as 别名]
# 或者: from tensorflow.contrib.slim.layers import conv2d [as 别名]
def basic_conv_lstm_cell(inputs,
                         state,
                         num_channels,
                         filter_size=5,
                         forget_bias=1.0,
                         scope=None,
                         reuse=None):
    """Basic LSTM recurrent network cell, with 2D convolution connctions.
    We add forget_bias (default: 1) to the biases of the forget gate in order to
    reduce the scale of forgetting in the beginning of the training.
    It does not allow cell clipping, a projection layer, and does not
    use peep-hole connections: it is the basic baseline.
    Args:
        inputs: input Tensor, 4D, batch x height x width x channels.
        state: state Tensor, 4D, batch x height x width x channels.
        num_channels: the number of output channels in the layer.
        filter_size: the shape of the each convolution filter.
        forget_bias: the initial value of the forget biases.
        scope: Optional scope for variable_scope.
        reuse: whether or not the layer and the variables should be reused.
    Returns:
         a tuple of tensors representing output and the new state.
    """
    spatial_size = inputs.get_shape()[1:3]
    if state is None:
        state = init_state(inputs, list(spatial_size) + [2 * num_channels])
    with tf.variable_scope(scope,
                           'BasicConvLstmCell',
                           [inputs, state],
                           reuse=reuse):
        inputs.get_shape().assert_has_rank(4)
        state.get_shape().assert_has_rank(4)
        c, h = tf.split(axis=3, num_or_size_splits=2, value=state)
        inputs_h = tf.concat(axis=3, values=[inputs, h])
        # Parameters of gates are concatenated into one conv for efficiency.
        i_j_f_o = layers.conv2d(inputs_h,
                                4 * num_channels, [filter_size, filter_size],
                                stride=1,
                                activation_fn=None,
                                scope='Gates')

        # i = input_gate, j = new_input, f = forget_gate, o = output_gate
        i, j, f, o = tf.split(axis=3, num_or_size_splits=4, value=i_j_f_o)

        new_c = c * tf.sigmoid(f + forget_bias) + tf.sigmoid(i) * tf.tanh(j)
        new_h = tf.tanh(new_c) * tf.sigmoid(o)

        return new_h, tf.concat(axis=3, values=[new_c, new_h]) 
开发者ID:alexlee-gk,项目名称:video_prediction,代码行数:50,代码来源:sv2p_model.py

示例4: basic_conv_lstm_cell

# 需要导入模块: from tensorflow.contrib.slim import layers [as 别名]
# 或者: from tensorflow.contrib.slim.layers import conv2d [as 别名]
def basic_conv_lstm_cell(inputs,
                         state,
                         num_channels,
                         filter_size=5,
                         forget_bias=1.0,
                         scope=None,
                         reuse=None):
  """Basic LSTM recurrent network cell, with 2D convolution connctions.

  We add forget_bias (default: 1) to the biases of the forget gate in order to
  reduce the scale of forgetting in the beginning of the training.

  It does not allow cell clipping, a projection layer, and does not
  use peep-hole connections: it is the basic baseline.

  Args:
    inputs: input Tensor, 4D, batch x height x width x channels.
    state: state Tensor, 4D, batch x height x width x channels.
    num_channels: the number of output channels in the layer.
    filter_size: the shape of the each convolution filter.
    forget_bias: the initial value of the forget biases.
    scope: Optional scope for variable_scope.
    reuse: whether or not the layer and the variables should be reused.

  Returns:
     a tuple of tensors representing output and the new state.
  """
  spatial_size = inputs.get_shape()[1:3]
  if state is None:
    state = init_state(inputs, list(spatial_size) + [2 * num_channels])
  with tf.variable_scope(scope,
                         'BasicConvLstmCell',
                         [inputs, state],
                         reuse=reuse):
    inputs.get_shape().assert_has_rank(4)
    state.get_shape().assert_has_rank(4)
    c, h = tf.split(3, 2, state)
    inputs_h = tf.concat(3, [inputs, h])
    # Parameters of gates are concatenated into one conv for efficiency.
    i_j_f_o = layers.conv2d(inputs_h,
                            4 * num_channels, [filter_size, filter_size],
                            stride=1,
                            activation_fn=None,
                            scope='Gates')

    # i = input_gate, j = new_input, f = forget_gate, o = output_gate
    i, j, f, o = tf.split(3, 4, i_j_f_o)

    new_c = c * tf.sigmoid(f + forget_bias) + tf.sigmoid(i) * tf.tanh(j)
    new_h = tf.tanh(new_c) * tf.sigmoid(o)

    return new_h, tf.concat(3, [new_c, new_h]) 
开发者ID:coderSkyChen,项目名称:Action_Recognition_Zoo,代码行数:54,代码来源:lstm_ops.py


注:本文中的tensorflow.contrib.slim.layers.conv2d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。