当前位置: 首页>>代码示例>>Python>>正文


Python layers.convolution2d方法代码示例

本文整理汇总了Python中tensorflow.contrib.layers.convolution2d方法的典型用法代码示例。如果您正苦于以下问题:Python layers.convolution2d方法的具体用法?Python layers.convolution2d怎么用?Python layers.convolution2d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.layers的用法示例。


在下文中一共展示了layers.convolution2d方法的15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: model

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def model(img_in, num_actions, scope, reuse=False, layer_norm=False):
    """As described in https://storage.googleapis.com/deepmind-data/assets/papers/DeepMindNature14236Paper.pdf"""
    with tf.variable_scope(scope, reuse=reuse):
        out = img_in
        with tf.variable_scope("convnet"):
            # original architecture
            out = layers.convolution2d(out, num_outputs=32, kernel_size=8, stride=4, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=4, stride=2, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=3, stride=1, activation_fn=tf.nn.relu)
        conv_out = layers.flatten(out)

        with tf.variable_scope("action_value"):
            value_out = layers.fully_connected(conv_out, num_outputs=512, activation_fn=None)
            if layer_norm:
                value_out = layer_norm_fn(value_out, relu=True)
            else:
                value_out = tf.nn.relu(value_out)
            value_out = layers.fully_connected(value_out, num_outputs=num_actions, activation_fn=None)
        return value_out 
开发者ID:AdamStelmaszczyk,项目名称:learning2run,代码行数:21,代码来源:model.py

示例2: model

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def model(img_in, num_actions, scope, noisy=False, reuse=False):
    """As described in https://storage.googleapis.com/deepmind-data/assets/papers/DeepMindNature14236Paper.pdf"""
    with tf.variable_scope(scope, reuse=reuse):
        out = img_in
        with tf.variable_scope("convnet"):
            # original architecture
            out = layers.convolution2d(out, num_outputs=32, kernel_size=8, stride=4, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=4, stride=2, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=3, stride=1, activation_fn=tf.nn.relu)
        out = layers.flatten(out)

        with tf.variable_scope("action_value"):
            if noisy:
                # Apply noisy network on fully connected layers
                # ref: https://arxiv.org/abs/1706.10295
                out = noisy_dense(out, name='noisy_fc1', size=512, activation_fn=tf.nn.relu)
                out = noisy_dense(out, name='noisy_fc2', size=num_actions)
            else:
                out = layers.fully_connected(out, num_outputs=512, activation_fn=tf.nn.relu)
                out = layers.fully_connected(out, num_outputs=num_actions, activation_fn=None)

        return out 
开发者ID:wenh123,项目名称:NoisyNet-DQN,代码行数:24,代码来源:model.py

示例3: model

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def model(img_in, num_actions, scope, reuse=False, concat_softmax=False):
    """As described in https://storage.googleapis.com/deepmind-data/assets/papers/DeepMindNature14236Paper.pdf"""
    with tf.variable_scope(scope, reuse=reuse):
        out = img_in
        with tf.variable_scope("convnet"):
            # original architecture
            out = layers.convolution2d(out, num_outputs=32, kernel_size=8, stride=4, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=4, stride=2, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=3, stride=1, activation_fn=tf.nn.relu)
        out = layers.flatten(out)

        with tf.variable_scope("action_value"):
            out = layers.fully_connected(out, num_outputs=512, activation_fn=tf.nn.relu)
            out = layers.fully_connected(out, num_outputs=num_actions, activation_fn=None)
            if concat_softmax:
                out = tf.nn.softmax(out)

        return out 
开发者ID:yenchenlin,项目名称:rl-attack-detection,代码行数:20,代码来源:model.py

示例4: dueling_model

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def dueling_model(img_in, num_actions, scope, reuse=False):
    """As described in https://arxiv.org/abs/1511.06581"""
    with tf.variable_scope(scope, reuse=reuse):
        out = img_in
        with tf.variable_scope("convnet"):
            # original architecture
            out = layers.convolution2d(out, num_outputs=32, kernel_size=8, stride=4, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=4, stride=2, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=3, stride=1, activation_fn=tf.nn.relu)
        out = layers.flatten(out)

        with tf.variable_scope("state_value"):
            state_hidden = layers.fully_connected(out, num_outputs=512, activation_fn=tf.nn.relu)
            state_score = layers.fully_connected(state_hidden, num_outputs=1, activation_fn=None)
        with tf.variable_scope("action_value"):
            actions_hidden = layers.fully_connected(out, num_outputs=512, activation_fn=tf.nn.relu)
            action_scores = layers.fully_connected(actions_hidden, num_outputs=num_actions, activation_fn=None)
            action_scores_mean = tf.reduce_mean(action_scores, 1)
            action_scores = action_scores - tf.expand_dims(action_scores_mean, 1)

        return state_score + action_scores 
开发者ID:yenchenlin,项目名称:rl-attack-detection,代码行数:23,代码来源:model.py

示例5: make_cnn

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def make_cnn(convs, padding, inpt, initializer=None):
    if initializer is None:
        initializer = tf.orthogonal_initializer(np.sqrt(2.0))
    out = inpt
    with tf.variable_scope('convnet'):
        for num_outputs, kernel_size, stride in convs:
            out = layers.convolution2d(
                out,
                num_outputs=num_outputs,
                kernel_size=kernel_size,
                stride=stride,
                padding=padding,
                activation_fn=tf.nn.relu,
                weights_initializer=initializer
            )
    return out 
开发者ID:takuseno,项目名称:ppo,代码行数:18,代码来源:network.py

示例6: __call__

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def __call__(self, h):
        # sequence -> [b, l, v]
        _, l, v = h.get_shape().as_list()
        h = tf.reshape(h, [-1, l, 1, v])
        with tf.variable_scope("textmover", reuse=tf.AUTO_REUSE):
            h0 = layers.convolution2d(
                h, v, [4, 1], [2, 1],
                activation_fn=tf.nn.softplus
            )
            h1 = layers.convolution2d(
                h0, v, [4, 1], [1, 1],
                activation_fn=tf.nn.softplus
            )
            h2 = layers.convolution2d(
                h1, v, [4, 1], [2, 1],
                activation_fn=tf.nn.softplus
            )
            h = layers.flatten(h2)
            h = layers.fully_connected(
                h, 1, activation_fn=tf.identity
            )
            return h 
开发者ID:desire2020,项目名称:CoT,代码行数:24,代码来源:mediator.py

示例7: model

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def model(img_in, num_actions, scope, reuse=False, layer_norm=False, distributed=False, atoms=51):
    """As described in https://storage.googleapis.com/deepmind-data/assets/papers/DeepMindNature14236Paper.pdf"""
    print("create default model: distributed? ", distributed, "atoms", atoms)
    with tf.variable_scope(scope, reuse=reuse):
        out = img_in
        with tf.variable_scope("convnet"):
            # original architecture
            out = layers.convolution2d(out, num_outputs=32, kernel_size=8, stride=4, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=4, stride=2, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=3, stride=1, activation_fn=tf.nn.relu)
        conv_out = layers.flatten(out)

        with tf.variable_scope("action_value"):
            value_out = layers.fully_connected(conv_out, num_outputs=512, activation_fn=None)
            if layer_norm:
                value_out = layer_norm_fn(value_out, relu=True)
            else:
                value_out = tf.nn.relu(value_out)
            value_out = layers.fully_connected(value_out, num_outputs=num_actions*atoms, activation_fn=None)
            if distributed:
                value_out = tf.reshape(value_out, [-1, num_actions, atoms])
        print("output shape:", tf.shape(value_out))
        return value_out 
开发者ID:cxxgtxy,项目名称:deeprl-baselines,代码行数:25,代码来源:model.py

示例8: model

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def model(img_in, num_actions, scope, reuse=False):
    """As described in https://storage.googleapis.com/deepmind-data/assets/papers/DeepMindNature14236Paper.pdf"""
    with tf.variable_scope(scope, reuse=reuse):
        out = img_in
        with tf.variable_scope("convnet"):
            # original architecture
            out = layers.convolution2d(out, num_outputs=32, kernel_size=8, stride=4, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=4, stride=2, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=3, stride=1, activation_fn=tf.nn.relu)
        out = layers.flatten(out)

        with tf.variable_scope("action_value"):
            out = layers.fully_connected(out, num_outputs=512, activation_fn=tf.nn.relu)
            out = layers.fully_connected(out, num_outputs=num_actions, activation_fn=None)

        return out 
开发者ID:LinZichuan,项目名称:emdqn,代码行数:18,代码来源:model.py

示例9: model

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def model(img_in, num_actions, scope, noisy=False, reuse=False,
          concat_softmax=False):
    with tf.variable_scope(scope, reuse=reuse):
        out = img_in
        with tf.variable_scope("convnet"):
            # original architecture
            out = layers.convolution2d(out, num_outputs=32, kernel_size=8,
                                       stride=4, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=4,
                                       stride=2, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=3,
                                       stride=1, activation_fn=tf.nn.relu)
        out = layers.flatten(out)

        with tf.variable_scope("action_value"):
            if noisy:
                # Apply noisy network on fully connected layers
                # ref: https://arxiv.org/abs/1706.10295
                out = noisy_dense(out, name='noisy_fc1', size=512,
                                  activation_fn=tf.nn.relu)
                out = noisy_dense(out, name='noisy_fc2', size=num_actions)
            else:
                out = layers.fully_connected(out, num_outputs=512,
                                             activation_fn=tf.nn.relu)
                out = layers.fully_connected(out, num_outputs=num_actions,
                                             activation_fn=None)
            # V: Softmax - inspired by deep-rl-attack #
            if concat_softmax:
                out = tf.nn.softmax(out)
        return out 
开发者ID:StephanZheng,项目名称:neural-fingerprinting,代码行数:32,代码来源:model.py

示例10: atari_model

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def atari_model(img_in, num_actions, scope, reuse=False):
    # as described in https://storage.googleapis.com/deepmind-data/assets/papers/DeepMindNature14236Paper.pdf
    with tf.variable_scope(scope, reuse=reuse):
        out = img_in
        with tf.variable_scope("convnet"):
            # original architecture
            out = layers.convolution2d(out, num_outputs=32, kernel_size=8, stride=4, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=4, stride=2, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=3, stride=1, activation_fn=tf.nn.relu)
        out = layers.flatten(out)
        with tf.variable_scope("action_value"):
            out = layers.fully_connected(out, num_outputs=512,         activation_fn=tf.nn.relu)
            out = layers.fully_connected(out, num_outputs=num_actions, activation_fn=None)

        return out 
开发者ID:xuwd11,项目名称:cs294-112_hws,代码行数:17,代码来源:run_dqn_atari.py

示例11: _cnn_to_mlp

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def _cnn_to_mlp(convs, hiddens, dueling, inpt, num_actions, scope, reuse=False, layer_norm=False):
    with tf.variable_scope(scope, reuse=reuse):
        out = inpt
        with tf.variable_scope("convnet"):
            for num_outputs, kernel_size, stride in convs:
                out = layers.convolution2d(out,
                                           num_outputs=num_outputs,
                                           kernel_size=kernel_size,
                                           stride=stride,
                                           activation_fn=tf.nn.relu)
        conv_out = layers.flatten(out)
        with tf.variable_scope("action_value"):
            action_out = conv_out
            for hidden in hiddens:
                action_out = layers.fully_connected(action_out, num_outputs=hidden, activation_fn=None)
                if layer_norm:
                    action_out = layers.layer_norm(action_out, center=True, scale=True)
                action_out = tf.nn.relu(action_out)
            action_scores = layers.fully_connected(action_out, num_outputs=num_actions, activation_fn=None)

        if dueling:
            with tf.variable_scope("state_value"):
                state_out = conv_out
                for hidden in hiddens:
                    state_out = layers.fully_connected(state_out, num_outputs=hidden, activation_fn=None)
                    if layer_norm:
                        state_out = layers.layer_norm(state_out, center=True, scale=True)
                    state_out = tf.nn.relu(state_out)
                state_score = layers.fully_connected(state_out, num_outputs=1, activation_fn=None)
            action_scores_mean = tf.reduce_mean(action_scores, 1)
            action_scores_centered = action_scores - tf.expand_dims(action_scores_mean, 1)
            q_out = state_score + action_scores_centered
        else:
            q_out = action_scores
        return q_out 
开发者ID:Hwhitetooth,项目名称:lirpg,代码行数:37,代码来源:models.py

示例12: conv_only

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def conv_only(convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)], **conv_kwargs):
    ''' 
    convolutions-only net

    Parameters:
    ----------

    conv:       list of triples (filter_number, filter_size, stride) specifying parameters for each layer. 

    Returns:

    function that takes tensorflow tensor as input and returns the output of the last convolutional layer
    
    '''

    def network_fn(X):
        out = tf.cast(X, tf.float32) / 255.
        with tf.variable_scope("convnet"):
            for num_outputs, kernel_size, stride in convs:
                out = layers.convolution2d(out,
                                           num_outputs=num_outputs,
                                           kernel_size=kernel_size,
                                           stride=stride,
                                           activation_fn=tf.nn.relu,
                                           **conv_kwargs)

        return out, None
    return network_fn 
开发者ID:MaxSobolMark,项目名称:HardRLWithYoutube,代码行数:30,代码来源:models.py

示例13: conv_only

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def conv_only(convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)], **conv_kwargs):
    '''
    convolutions-only net

    Parameters:
    ----------

    conv:       list of triples (filter_number, filter_size, stride) specifying parameters for each layer.

    Returns:

    function that takes tensorflow tensor as input and returns the output of the last convolutional layer

    '''

    def network_fn(X):
        out = tf.cast(X, tf.float32) / 255.
        with tf.variable_scope("convnet"):
            for num_outputs, kernel_size, stride in convs:
                out = layers.convolution2d(out,
                                           num_outputs=num_outputs,
                                           kernel_size=kernel_size,
                                           stride=stride,
                                           activation_fn=tf.nn.relu,
                                           **conv_kwargs)

        return out
    return network_fn 
开发者ID:quantumiracle,项目名称:Reinforcement_Learning_for_Traffic_Light_Control,代码行数:30,代码来源:models.py

示例14: dueling_model

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def dueling_model(img_in, num_actions, scope, reuse=False, layer_norm=False):
    """As described in https://arxiv.org/abs/1511.06581"""
    with tf.variable_scope(scope, reuse=reuse):
        out = img_in
        with tf.variable_scope("convnet"):
            # original architecture
            out = layers.convolution2d(out, num_outputs=32, kernel_size=8, stride=4, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=4, stride=2, activation_fn=tf.nn.relu)
            out = layers.convolution2d(out, num_outputs=64, kernel_size=3, stride=1, activation_fn=tf.nn.relu)
        conv_out = layers.flatten(out)

        with tf.variable_scope("state_value"):
            state_hidden = layers.fully_connected(conv_out, num_outputs=512, activation_fn=None)
            if layer_norm:
                state_hidden = layer_norm_fn(state_hidden, relu=True)
            else:
                state_hidden = tf.nn.relu(state_hidden)
            state_score = layers.fully_connected(state_hidden, num_outputs=1, activation_fn=None)
        with tf.variable_scope("action_value"):
            actions_hidden = layers.fully_connected(conv_out, num_outputs=512, activation_fn=None)
            if layer_norm:
                actions_hidden = layer_norm_fn(actions_hidden, relu=True)
            else:
                actions_hidden = tf.nn.relu(actions_hidden)
            action_scores = layers.fully_connected(actions_hidden, num_outputs=num_actions, activation_fn=None)
            action_scores_mean = tf.reduce_mean(action_scores, 1)
            action_scores = action_scores - tf.expand_dims(action_scores_mean, 1)
        return state_score + action_scores 
开发者ID:AdamStelmaszczyk,项目名称:learning2run,代码行数:30,代码来源:model.py

示例15: _cnn_to_mlp

# 需要导入模块: from tensorflow.contrib import layers [as 别名]
# 或者: from tensorflow.contrib.layers import convolution2d [as 别名]
def _cnn_to_mlp(convs, hiddens, dueling, inpt, num_actions, scope, reuse=False, layer_norm=False, data_format=None):
    with tf.variable_scope(scope, reuse=reuse):
        out = inpt
        with tf.variable_scope("convnet"):
            for num_outputs, kernel_size, stride in convs:
                out = layers.convolution2d(out,
                                           num_outputs=num_outputs,
                                           kernel_size=kernel_size,
                                           stride=stride,
                                           activation_fn=tf.nn.relu,
                                           data_format=data_format)
        conv_out = layers.flatten(out)
        with tf.variable_scope("action_value"):
            action_out = conv_out
            for hidden in hiddens:
                action_out = layers.fully_connected(action_out, num_outputs=hidden, activation_fn=None)
                if layer_norm:
                    action_out = layers.layer_norm(action_out, center=True, scale=True)
                action_out = tf.nn.relu(action_out)
            action_scores = layers.fully_connected(action_out, num_outputs=num_actions, activation_fn=None)

        if dueling:
            with tf.variable_scope("state_value"):
                state_out = conv_out
                for hidden in hiddens:
                    state_out = layers.fully_connected(state_out, num_outputs=hidden, activation_fn=None)
                    if layer_norm:
                        state_out = layers.layer_norm(state_out, center=True, scale=True)
                    state_out = tf.nn.relu(state_out)
                state_score = layers.fully_connected(state_out, num_outputs=1, activation_fn=None)
            action_scores_mean = tf.reduce_mean(action_scores, 1)
            action_scores_centered = action_scores - tf.expand_dims(action_scores_mean, 1)
            q_out = state_score + action_scores_centered
        else:
            q_out = action_scores
        return q_out 
开发者ID:uber-research,项目名称:ape-x,代码行数:38,代码来源:models.py


注:本文中的tensorflow.contrib.layers.convolution2d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。