3、tensorflow构建网络

with slim.arg_scope([slim.conv2d, slim.fully_connected],
                         activation_fn=tf.nn.relu,
                         weights_initializer=tf.glorot_uniform_initializer(),　　　　　　　　　　　　　　　　

　　　　　　　　　　　　　　　　#weight_initializer=tf.contrib.layers.xavier_initializer_conv2d()#CNN用这个进行初始化,去掉_conv2d用于初始化fc

　　　　　　　　　　　　　　#weights_initializer= tf.contrib.layers.variance_scaling_initializer( )，

                         biases_initializer=tf.constant_initializer(0)):
        
        net = slim.conv2d(inputs, 64, [11, 11], 4)#步长默认是1，这里改成4了；64是输出特征图个数
        net = slim.max_pool2d(net, [3, 3])
        net = slim.conv2d(net, 192, [5, 5])
        net = slim.max_pool2d(net, [3, 3])
        net = slim.conv2d(net, 384, [3, 3])
        net = slim.conv2d(net, 384, [3, 3])
        net = slim.conv2d(net, 256, [3, 3])
        net = slim.max_pool2d(net, [3, 3])
        
        # 数据扁平化
        net = slim.flatten(net)
        net = slim.fully_connected(net, 1024)
        net = slim.dropout(net, is_training=is_training)
        
        net0 = slim.fully_connected(net, num_classes, activation_fn=tf.nn.softmax)
        net1 = slim.fully_connected(net, num_classes, activation_fn=tf.nn.softmax)
        net2 = slim.fully_connected(net, num_classes, activation_fn=tf.nn.softmax)
        net3 = slim.fully_connected(net, num_classes, activation_fn=tf.nn.softmax)

BN层：

net = tf.layers.batch_normalization(net,

trainable=True,#如果是True，就表示这个batch normalization后，会经过一个线性变换

　　　　　　　　　　　　　　　　　　　　　　training=is_training)#是训练模式，还是测试模式，测试模式会利用训练模式的均值和方差

L2正则化

方法一

weight_decay = 0.001

base_loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(labels=labels, logits=logits))

l2_loss = weight_decay * tf.add_n([tf.nn.l2_loss(tf.cast(v, tf.float32)) for v in tf.trainable_variables()])

loss = base_loss + l2_loss

方法二
x = tf.layers.conv2d(x, 512, (3, 3),
                             padding='same',
                             activation=tf.nn.relu,
                             kernel_initializer=tf.truncated_normal_initializer(stddev=0.01),
                             kernel_regularizer=tf.contrib.layers.l2_regularizer(0.001)

base_loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(labels=labels, logits=logits))
l2_loss = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
loss = tf.add_n([base_loss] + l2_loss, name="loss")