TF.Slim的repeat和stack操作

• 2019 年 10 月 28 日
• 筆記

版權聲明：本文為部落客原創文章，遵循 CC 4.0 BY-SA 版權協議，轉載請附上原文出處鏈接和本聲明。

本文鏈接：https://blog.csdn.net/weixin_36670529/article/details/102723445

一、常規做法

在搭建網路時，TF-Slim 提供 repeat 和 stack，允許用戶重複執行相同的 操作，方便網路構建，例如：

net = ...  net = slim.conv2d(net, 256, [3, 3], scope='conv3_1')  net = slim.conv2d(net, 256, [3, 3], scope='conv3_2')  net = slim.conv2d(net, 256, [3, 3], scope='conv3_3')  net = slim.max_pool2d(net, [2, 2], scope='pool2')

常見的作法：可用循環減少工作

net = ...  for i in range(3):     net = slim.conv2d(net, 256, [3, 3], scope='conv3_%d' % (i+1))     net = slim.max_pool2d(net, [2, 2], scope='pool2')

二、TF-Slim 中的 repeat 操作

使用 TF-Slim 中的 repeat 操作替代上邊的定義：

net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3')  net = slim.max_pool2d(net, [2, 2], scope='pool2')

slim.repeat 會自動給每一個卷積層的scopes命名為』conv3/conv3_1』, 』conv3/conv3_2』 和』conv3/conv3_3』

三、TF-Slim 中的 stack操作

TF-Slim 的 slim.stack 操作允許用戶用不同的參數重複調用同一種操作 slim.stack 也為每一個被創建的操作創建一個新的 tf.variable_scope

# Verbose way:原始操作  x = slim.fully_connected(x, 32, scope='fc/fc_1')  x = slim.fully_connected(x, 64, scope='fc/fc_2')  x = slim.fully_connected(x, 128, scope='fc/fc_3')    # Equivalent , TF-Slim way using slim.stack:等價操作  slim.stack(x, slim.fully_connected , [32, 64, 128], scope='fc')    # slim.stack 調用了 slim.fully_connected 三次

看到repeat和stack在細節上有差異。具體查看文檔

例子，定義vgg

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)):  # with之下              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

基於slim的vgg框架：

import tensorflow as tf  import tensorflow.contrib.slim.nets as nets    slim = tf.contrib.slim  vgg = nets.vgg    ...    train_log_dir = ...  if not tf.gfile.Exists(train_log_dir):          tf.gfile.MakeDirs(train_log_dir)    with tf.Graph().as_default():          # Set up the data loading:          images, labels = ...            # Define the model:          predictions = vgg.vgg_16(images, is_training=True)            # Specify the loss function:          slim.losses.softmax_cross_entropy(predictions , labels)            total_loss = slim.losses.get_total_loss()          tf.summary.scalar('losses/total_loss', total_loss)            # Specify the optimization scheme:          optimizer = tf.train.GradientDescentOptimizer(learning_rate=.001)            # create_train_op that ensures that when we evaluate it to get the loss,          # the update_ops are done and the gradient updates are computed.          train_tensor = slim.learning.create_train_op(total_loss , optimizer)            # Actually runs training.          slim.learning.train(train_tensor , train_log_dir)