TFslim - 为 VGG16 加载保存的检查点时出现问题

Question

(1) 我试图通过将预训练权重加载到除 fc8 层之外的所有层来使用 TFslim 微调 VGG-16 网络。我通过使用 TF-SLIm 函数实现了这一点，如下所示：

import tensorflow as tf
import tensorflow.contrib.slim as slim
import tensorflow.contrib.slim.nets as nets

vgg = nets.vgg

# Specify where the Model, trained on ImageNet, was saved.
model_path = 'path/to/vgg_16.ckpt'

# Specify where the new model will live:
log_dir = 'path/to/log/'

images = tf.placeholder(tf.float32, [None, 224, 224, 3])
predictions = vgg.vgg_16(images)

variables_to_restore = slim.get_variables_to_restore(exclude=['fc8'])
restorer = tf.train.Saver(variables_to_restore)




init = tf.initialize_all_variables()

with tf.Session() as sess:
   sess.run(init)
   restorer.restore(sess,model_path)
   print "model restored"

只要我不更改 VGG16 模型的 num_classes，它就可以正常工作。我想做的是将 num_classes 从 1000 更改为 200。我的印象是，如果我通过定义一个新的 vgg16-modified class 来替换 fc8 产生 200 个输出，（连同 variables_to_restore = slim.get_variables_to_restore(exclude=['fc8']) 一切都会好起来的。但是，tensorflow 抱怨尺寸不匹配：

InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [1,1,4096,200] rhs shape= [1,1,4096,1000]

那么，如何才能真正做到这一点呢？ TFslim 的文档确实是零散的，Github 上散布着几个版本 - 所以在那里没有太多帮助。

Answer 1

你可以试试slim的恢复方式——slim.assign_from_checkpoint.

slim源中有相关文档： https://github.com/tensorflow/tensorflow/blob/129665119ea60640f7ed921f36db9b5c23455224/tensorflow/contrib/slim/python/slim/learning.py

对应部分：

*************************************************
* Fine-Tuning Part of a model from a checkpoint *
*************************************************
Rather than initializing all of the weights of a given model, we sometimes
only want to restore some of the weights from a checkpoint. To do this, one
need only filter those variables to initialize as follows:
  ...
  # Create the train_op
  train_op = slim.learning.create_train_op(total_loss, optimizer)
  checkpoint_path = '/path/to/old_model_checkpoint'
  # Specify the variables to restore via a list of inclusion or exclusion
  # patterns:
  variables_to_restore = slim.get_variables_to_restore(
      include=["conv"], exclude=["fc8", "fc9])
  # or
  variables_to_restore = slim.get_variables_to_restore(exclude=["conv"])
  init_assign_op, init_feed_dict = slim.assign_from_checkpoint(
      checkpoint_path, variables_to_restore)
  # Create an initial assignment function.
  def InitAssignFn(sess):
      sess.run(init_assign_op, init_feed_dict)
  # Run training.
  slim.learning.train(train_op, my_log_dir, init_fn=InitAssignFn)

更新

我尝试了以下方法：

import tensorflow as tf
import tensorflow.contrib.slim as slim
import tensorflow.contrib.slim.nets as nets
images = tf.placeholder(tf.float32, [None, 224, 224, 3])
predictions = nets.vgg.vgg_16(images)
print [v.name for v in slim.get_variables_to_restore(exclude=['fc8']) ]

得到这个输出（缩短）：

[u'vgg_16/conv1/conv1_1/weights:0',
 u'vgg_16/conv1/conv1_1/biases:0',
 …
 u'vgg_16/fc6/weights:0',
 u'vgg_16/fc6/biases:0',
 u'vgg_16/fc7/weights:0',
 u'vgg_16/fc7/biases:0',
 u'vgg_16/fc8/weights:0',
 u'vgg_16/fc8/biases:0']

所以看起来你应该在范围前加上 vgg_16:

print [v.name for v in slim.get_variables_to_restore(exclude=['vgg_16/fc8']) ]

给出（缩写）：

[u'vgg_16/conv1/conv1_1/weights:0',
 u'vgg_16/conv1/conv1_1/biases:0',
 …
 u'vgg_16/fc6/weights:0',
 u'vgg_16/fc6/biases:0',
 u'vgg_16/fc7/weights:0',
 u'vgg_16/fc7/biases:0']

更新 2

完整示例（在我的系统中）执行无误。

import tensorflow as tf
import tensorflow.contrib.slim as slim
import tensorflow.contrib.slim.nets as nets

s = tf.Session(config=tf.ConfigProto(gpu_options={'allow_growth':True}))

images = tf.placeholder(tf.float32, [None, 224, 224, 3])
predictions = nets.vgg.vgg_16(images, 200)
variables_to_restore = slim.get_variables_to_restore(exclude=['vgg_16/fc8'])
init_assign_op, init_feed_dict = slim.assign_from_checkpoint('./vgg16.ckpt', variables_to_restore)
s.run(init_assign_op, init_feed_dict)

在上面的示例中，vgg16.ckpt 是 tf.train.Saver 为 1000 类 VGG16 模型保存的检查点。

将此检查点与 200 类模型（包括 fc8）的所有变量一起使用会出现以下错误：

init_assign_op, init_feed_dict = slim.assign_from_checkpoint('./vgg16.ckpt', slim.get_variables_to_restore())
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
      1 init_assign_op, init_feed_dict = slim.assign_from_checkpoint(
----> 2       './vgg16.ckpt', slim.get_variables_to_restore())

/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/framework/python/ops/variables.pyc in assign_from_checkpoint(model_path, var_list)
    527     assign_ops.append(var.assign(placeholder_value))
    528
--> 529     feed_dict[placeholder_value] = var_value.reshape(var.get_shape())
    530
    531   assign_op = control_flow_ops.group(*assign_ops)

ValueError: total size of new array must be unchanged

TFslim - 为 VGG16 加载保存的检查点时出现问题

TFSlim - problems loading saved checkpoint for VGG16

tensorflow

tf-slim