TF：卷积层的实现方式

最新推荐文章于 2023-09-01 16:49:01 发布

qq_26697045

最新推荐文章于 2023-09-01 16:49:01 发布

阅读量556

点赞数

CC 4.0 BY-SA版权

分类专栏：深度学习基础s

本文链接：https://blog.youkuaiyun.com/qq_26697045/article/details/89322285

深度学习基础s 专栏收录该内容

64 篇文章

订阅专栏

本文详细介绍了三种卷积层的实现方法：基础的tf.nn.conv2d，高级API tf.contrib.layers.conv2d，以及更高级的tf.contrib.slim.conv2d。通过具体的代码示例，展示了如何使用这些方法创建权重、偏置和卷积层，以及如何利用重复函数快速定义VGG16模型。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

卷积层的实现方式：

tf.nn.conv2d：最基础的用法，需要自定义权重和偏置。用法示例：

def create_weights(shape):
    return tf.Variable(tf.truncated_normal(shape,stddev=0.1))

def create_bias(num_filters):
    return tf.Variable(tf.constant(0.05,shape=num_filters))

def create_conv_layer(input,num_channels,filtr_size,num_filters):
    weights=create_weights(shape=[input,num_channels,filtr_size,num_filter])
    bias=create_bias(num_filters)
    layer=tf.nn.conv2d(input=input,filter=weights,stride=[1,1,1,1],padding='same')
    layer+=bias
    layer=tf.nn.max_pool(layer,ksize=[1,2,2,1],strides=[1,2,2,1],padding='same')
    return layer

tf.contrib.layers.conv2d：高级API。用法示例：

tf.nn.conv2d(
    input,
    filter,
    strides,
    padding,
    use_cudnn_on_gpu=True,
    data_format='NHWC',
    dilations=[1, 1, 1, 1],
    name=None
)

tf.contrib.slim.conv2d：更高级的API。用法示例：

def mynet(input,reuse=False):
    with tf.variable_scope("conv1") as scope:
        net=tf.contrib.layers.conv2d(input,
				     32,
				     [5,5],
				     padding='SAME',
				     weights_initializer=tf.contrib.layers.xavier_initializer(uniform=False),
				     scope=scope,
				     reuse=reuse)
        net=tf.contrib.layers.max_pool2d(net,
					 [2,2],
					 padding='SAME')
    with tf.variable_scope("conv2") as scope:
        ...
    net=tf.contrib.layers.flatten(net)
    return net

它的repeat函数可以快速定义层，如定义VGG16模型：

def vgg16(inputs):
  with slim.arg_scope([slim.conv2d, slim.fully_connected],
                      activation_fn=tf.nn.relu,
                      weights_initializer=tf.truncated_normal_initializer(0.0, 0.01),
                      weights_regularizer=slim.l2_regularizer(0.0005)):
    net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1')
    net = slim.max_pool2d(net, [2, 2], scope='pool1')
    net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2')
    net = slim.max_pool2d(net, [2, 2], scope='pool2')
    net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3')
    net = slim.max_pool2d(net, [2, 2], scope='pool3')
    net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4')
    net = slim.max_pool2d(net, [2, 2], scope='pool4')
    net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5')
    net = slim.max_pool2d(net, [2, 2], scope='pool5')
    net = slim.fully_connected(net, 4096, scope='fc6')
    net = slim.dropout(net, 0.5, scope='dropout6')
    net = slim.fully_connected(net, 4096, scope='fc7')
    net = slim.dropout(net, 0.5, scope='dropout7')
    net = slim.fully_connected(net, 1000, activation_fn=None, scope='fc8')
  return net

[参考1][slim实现vgg][slim实现vgg]