Python tflearn.conv_2d方法代码示例

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def resnext(width, height, frame_count, lr, output=9, model_name = 'sentnet_color.model'):
    net = input_data(shape=[None, width, height, 3], name='input')
    net = tflearn.conv_2d(net, 16, 3, regularizer='L2', weight_decay=0.0001)
    net = tflearn.layers.conv.resnext_block(net, n, 16, 32)
    net = tflearn.resnext_block(net, 1, 32, 32, downsample=True)
    net = tflearn.resnext_block(net, n-1, 32, 32)
    net = tflearn.resnext_block(net, 1, 64, 32, downsample=True)
    net = tflearn.resnext_block(net, n-1, 64, 32)
    net = tflearn.batch_normalization(net)
    net = tflearn.activation(net, 'relu')
    net = tflearn.global_avg_pool(net)
    # Regression
    net = tflearn.fully_connected(net, output, activation='softmax')
    opt = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
    net = tflearn.regression(net, optimizer=opt,
                             loss='categorical_crossentropy')

    model = tflearn.DNN(net,
                        max_checkpoints=0, tensorboard_verbose=0, tensorboard_dir='log')

    return model 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def create_actor_network(self):
        with tf.variable_scope('actor'):
            inputs = tflearn.input_data(
                shape=[None, self.s_dim[0], self.s_dim[1]])
            _input = tf.expand_dims(inputs, -1)

            merge_net = tflearn.conv_2d(
                _input, FEATURE_NUM, KERNEL, activation='relu')
            merge_net = tflearn.conv_2d(
                merge_net, FEATURE_NUM, KERNEL, activation='relu')

            avg_net = tflearn.global_avg_pool(merge_net)
            out = tflearn.fully_connected(
                avg_net, self.a_dim, activation='softmax')

            return inputs, out 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def create_critic_network(self):
        with tf.variable_scope('critic'):
            inputs = tflearn.input_data(
                shape=[None, self.s_dim[0], self.s_dim[1]])
            _input = tf.expand_dims(inputs, -1)

            merge_net = tflearn.conv_2d(
                _input, FEATURE_NUM, KERNEL, activation='relu')
            merge_net = tflearn.conv_2d(
                merge_net, FEATURE_NUM, KERNEL, activation='relu')

            avg_net = tflearn.global_avg_pool(merge_net)
            # dense_net_0 = tflearn.fully_connected(
            #    merge_net, 64, activation='relu')
            #dense_net_0 = tflearn.dropout(dense_net_0, 0.8)
            out = tflearn.fully_connected(avg_net, 1, activation='linear')

            return inputs, out 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def vgg16(input, num_class):
    network = tflearn.conv_2d(
        input, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
    network = tflearn.avg_pool_2d(network, 2)
    network = tflearn.conv_2d(
        network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
    network = tflearn.avg_pool_2d(network, 2)
    network = tflearn.conv_2d(
        network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
    network = tflearn.avg_pool_2d(network, 2)
    network = tflearn.conv_2d(
        network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
    network = tflearn.avg_pool_2d(network, 2)

    x = tflearn.fully_connected(
        network, num_class, activation='sigmoid', scope='fc8')
    return x 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def CNN_Core(x, reuse=False):
    with tf.variable_scope('cnn_core', reuse=reuse):
        network = tflearn.conv_2d(
            x, KERNEL, 5, activation='relu', regularizer="L2", weight_decay=0.0001)
        network = tflearn.max_pool_2d(network, 2)
        network = tflearn.conv_2d(
            network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
        network = tflearn.max_pool_2d(network, 2)
        network = tflearn.conv_2d(
            network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
        network = tflearn.max_pool_2d(network, 2)
        network = tflearn.conv_2d(
            network, KERNEL // 2, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
        # network = tflearn.fully_connected(
        #   network, DENSE_SIZE, activation='relu')
        split_flat = tflearn.flatten(network)
        return split_flat 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def build_dqn(num_actions, action_repeat):
    """
    Building a DQN.
    """
    inputs = tf.placeholder(tf.float32, [None, action_repeat, 84, 84])
    # Inputs shape: [batch, channel, height, width] need to be changed into
    # shape [batch, height, width, channel]
    net = tf.transpose(inputs, [0, 2, 3, 1])
    net = tflearn.conv_2d(net, 32, 8, strides=4, activation='relu')
    net = tflearn.conv_2d(net, 64, 4, strides=2, activation='relu')
    net = tflearn.fully_connected(net, 256, activation='relu')
    q_values = tflearn.fully_connected(net, num_actions)
    return inputs, q_values


# =============================
#   ATARI Environment Wrapper
# ============================= 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def vgg_net_19(width, height):
    network = input_data(shape=[None, height, width, 3], name='input')
    network = conv_2d(network, 64, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 64, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 128, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 128, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = fully_connected(network, 4096, activation='relu', weight_decay=5e-4)
    network = dropout(network, keep_prob=0.5)
    network = fully_connected(network, 4096, activation='relu', weight_decay=5e-4)
    network = dropout(network, keep_prob=0.5)
    network = fully_connected(network, 1000, activation='softmax', weight_decay=5e-4)
    
    opt = Momentum(learning_rate=0, momentum = 0.9)
    network = regression(network, optimizer=opt, loss='categorical_crossentropy', name='targets')
    
    model = DNN(network, checkpoint_path='', max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir='')
    
    return model

#model of vgg-19 for testing of the activations 
#rename the output you want to test, connect it to the next layer and change the output layer at the bottom (model = DNN(...))
#make sure to use the correct test function (depending if your output is a tensor or a vector) 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def vgg_net_19_activations(width, height):
    network = input_data(shape=[None, height, width, 3], name='input')
    network1 = conv_2d(network, 64, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network2 = conv_2d(network1, 64, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network2, 2, strides=2)
    network = conv_2d(network, 128, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 128, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = fully_connected(network, 4096, activation='relu', weight_decay=5e-4)
    network = dropout(network, keep_prob=0.5)
    network = fully_connected(network, 4096, activation='relu', weight_decay=5e-4)
    network = dropout(network, keep_prob=0.5)
    network = fully_connected(network, 1000, activation='softmax', weight_decay=5e-4)
    
    opt = Momentum(learning_rate=0, momentum = 0.9)
    network = regression(network, optimizer=opt, loss='categorical_crossentropy', name='targets')
    
    model = DNN(network1, checkpoint_path='', max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir='')
    
    return model 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def sentnet_color_2d(width, height, frame_count, lr, output=9, model_name = 'sentnet_color.model'):
    network = input_data(shape=[None, width, height, 3], name='input')
    network = conv_2d(network, 96, 11, strides=4, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = conv_2d(network, 256, 5, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = conv_2d(network, 384, 3, activation='relu')
    network = conv_2d(network, 384, 3, activation='relu')
    network = conv_2d(network, 256, 3, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = conv_2d(network, 256, 5, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = conv_2d(network, 384, 3, activation='relu')
    network = conv_2d(network, 384, 3, activation='relu')
    network = conv_2d(network, 256, 3, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = fully_connected(network, 4096, activation='tanh')
    network = dropout(network, 0.5)
    network = fully_connected(network, 4096, activation='tanh')
    network = dropout(network, 0.5)
    network = fully_connected(network, 4096, activation='tanh')
    network = dropout(network, 0.5)
    network = fully_connected(network, 4096, activation='tanh')
    network = dropout(network, 0.5)
    network = fully_connected(network, output, activation='softmax')
    network = regression(network, optimizer='momentum',
                         loss='categorical_crossentropy',
                         learning_rate=lr, name='targets')

    model = tflearn.DNN(network,
                        max_checkpoints=0, tensorboard_verbose=0, tensorboard_dir='log')

    return model 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def alexnet2(width, height, lr, output=3):
    network = input_data(shape=[None, width, height, 1], name='input')
    network = conv_2d(network, 96, 11, strides=4, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = conv_2d(network, 256, 5, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = conv_2d(network, 384, 3, activation='relu')
    network = conv_2d(network, 384, 3, activation='relu')
    network = conv_2d(network, 256, 3, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = conv_2d(network, 256, 5, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = conv_2d(network, 384, 3, activation='relu')
    network = conv_2d(network, 384, 3, activation='relu')
    network = conv_2d(network, 256, 3, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = fully_connected(network, 4096, activation='tanh')
    network = dropout(network, 0.5)
    network = fully_connected(network, 4096, activation='tanh')
    network = dropout(network, 0.5)
    network = fully_connected(network, 4096, activation='tanh')
    network = dropout(network, 0.5)
    network = fully_connected(network, 4096, activation='tanh')
    network = dropout(network, 0.5)
    network = fully_connected(network, output, activation='softmax')
    network = regression(network, optimizer='momentum',
                         loss='categorical_crossentropy',
                         learning_rate=lr, name='targets')

    model = tflearn.DNN(network, checkpoint_path='model_alexnet',
                        max_checkpoints=1, tensorboard_verbose=0, tensorboard_dir='log')

    return model 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def alexnet(width, height, lr, output=3):
    network = input_data(shape=[None, width, height, 1], name='input')
    network = conv_2d(network, 96, 11, strides=4, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = conv_2d(network, 256, 5, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = conv_2d(network, 384, 3, activation='relu')
    network = conv_2d(network, 384, 3, activation='relu')
    network = conv_2d(network, 256, 3, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = fully_connected(network, 4096, activation='tanh')
    network = dropout(network, 0.5)
    network = fully_connected(network, 4096, activation='tanh')
    network = dropout(network, 0.5)
    network = fully_connected(network, output, activation='softmax')
    network = regression(network, optimizer='momentum',
                         loss='categorical_crossentropy',
                         learning_rate=lr, name='targets')

    model = tflearn.DNN(network, checkpoint_path='model_alexnet',
                        max_checkpoints=1, tensorboard_verbose=0, tensorboard_dir='log')

    return model 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def CNN_Core(x, reuse=False):
    with tf.variable_scope('cnn_core', reuse=reuse):
        network = tflearn.conv_2d(
            x, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
        network = tflearn.max_pool_2d(network, 2)
        cnn_network = tflearn.conv_2d(
            network, KERNEL * 2, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
        #network = tflearn.max_pool_2d(network, 2)
        # network = tflearn.conv_2d(
        #    network, KERNEL * 4, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
        #network = tflearn.max_pool_2d(network, 2)
        network = tflearn.global_avg_pool(cnn_network)
        split_flat = tflearn.flatten(network)
        #print split_flat.get_shape().as_list()
        return split_flat, cnn_network 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def CNN_Core(self, x, reuse=False):
        with tf.variable_scope('cnn_core', reuse=reuse):
            network = tflearn.conv_2d(
                x, KERNEL, 5, activation='relu', regularizer="L2", weight_decay=0.0001)
            network = tflearn.avg_pool_2d(network, 3)
            network = tflearn.conv_2d(
                network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
            network = tflearn.avg_pool_2d(network, 2)
            network = tflearn.fully_connected(
                network, DENSE_SIZE, activation='relu')
            split_flat = tflearn.flatten(network)
            return split_flat 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def vqn_model(self, x):
        with tf.variable_scope('vqn'):
            inputs = tflearn.input_data(placeholder=x)
            _split_array = []

            for i in range(INPUT_SEQ):
                tmp_network = tf.reshape(
                    inputs[:, i:i+1, :, :, :], [-1, INPUT_H, INPUT_W, INPUT_D])
                if i == 0:
                    _split_array.append(self.CNN_Core(tmp_network))
                else:
                    _split_array.append(self.CNN_Core(tmp_network, True))

            merge_net = tflearn.merge(_split_array, 'concat')
            merge_net = tflearn.flatten(merge_net)
            _count = merge_net.get_shape().as_list()[1]

            with tf.variable_scope('full-cnn'):
                net = tf.reshape(
                    merge_net, [-1, INPUT_SEQ, _count / INPUT_SEQ, 1])
                network = tflearn.conv_2d(
                    net, KERNEL, 5, activation='relu', regularizer="L2", weight_decay=0.0001)
                network = tflearn.max_pool_2d(network, 3)
                network = tflearn.layers.normalization.batch_normalization(
                    network)
                network = tflearn.conv_2d(
                    network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
                network = tflearn.max_pool_2d(network, 2)
                network = tflearn.layers.normalization.batch_normalization(
                    network)
                cnn_result = tflearn.fully_connected(
                    network, DENSE_SIZE, activation='relu')

        out = tflearn.fully_connected(
            cnn_result, OUTPUT_DIM, activation='sigmoid')

        return out 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import conv_2d [as 别名]
def CNN_Core(x,reuse=False):
    with tf.variable_scope('cnn_core',reuse=reuse):
        network = tflearn.conv_2d(
            x, KERNEL, 3, activation='relu', regularizer="L2",weight_decay=0.0001)
        network = tflearn.max_pool_2d(network, 2)
        network = tflearn.conv_2d(
        	network, KERNEL, 2, activation='relu', regularizer="L2",weight_decay=0.0001)
        network = tflearn.max_pool_2d(network, 2)
        network = tflearn.conv_2d(
              network, KERNEL, 2, activation='relu', regularizer="L2",weight_decay=0.0001)
        network = tflearn.max_pool_2d(network, 2)

        split_flat = tflearn.flatten(network)
        return split_flat