Python im2text&；TensorFlow 1.4.1

这里有人成功使用TensorFlow 1.4.1运行IM2Text吗

我正在使用这个模型（）

然后我尝试了以下脚本来转换模型。脚本生成了检查点、.meta、.data和.index

OLD_CHECKPOINT_FILE = "/tmp/my_checkpoint/model.ckpt-3000000"
NEW_CHECKPOINT_FILE = "/tmp/my_converted_checkpoint/model.ckpt-3000000"

import tensorflow as tf
vars_to_rename = {
    "lstm/BasicLSTMCell/Linear/Matrix": "lstm/basic_lstm_cell/weights",
    "lstm/BasicLSTMCell/Linear/Bias": "lstm/basic_lstm_cell/biases",
}
new_checkpoint_vars = {}
reader = tf.train.NewCheckpointReader(OLD_CHECKPOINT_FILE)
for old_name in reader.get_variable_to_shape_map():
  if old_name in vars_to_rename:
    new_name = vars_to_rename[old_name]
  else:
    new_name = old_name
  new_checkpoint_vars[new_name] = tf.Variable(reader.get_tensor(old_name))

init = tf.global_variables_initializer()
saver = tf.train.Saver(new_checkpoint_vars)

with tf.Session() as sess:
  sess.run(init)
  print("save checkpoint")
  saver.save(sess, NEW_CHECKPOINT_FILE)

谁能告诉我如何使用这些文件在TensorFlow 1.4.1中运行IM2Text。（实际上，我可以使用tensorflow 0.12.1运行IM2Text）

环境 python 3.5.2
Mac OS X版本10.12.6
TensorFlow 1.4.1

---

感谢您的帮助。

在MacOS 10.13上，tf 1.4.1和python3.5的检查点文件也会出现同样的错误

原因：下载的检查点文件是使用旧版本的tensorflow（python2）生成的。word_count.txt文件格式

来自

变化： 1.生成可由tf1.4.1加载的ckp文件

OLD_CHECKPOINT_FILE = "model.ckpt-1000000"
NEW_CHECKPOINT_FILE = "model2.ckpt-1000000"

import tensorflow as tf
vars_to_rename = {
"lstm/basic_lstm_cell/weights": "lstm/basic_lstm_cell/kernel",
"lstm/basic_lstm_cell/biases": "lstm/basic_lstm_cell/bias",
}
new_checkpoint_vars = {}
reader = tf.train.NewCheckpointReader(OLD_CHECKPOINT_FILE)
for old_name in reader.get_variable_to_shape_map():
    if old_name in vars_to_rename:
        new_name = vars_to_rename[old_name]
else:
    new_name = old_name
new_checkpoint_vars[new_name] = 
tf.Variable(reader.get_tensor(old_name))`

init = tf.global_variables_initializer()
saver = tf.train.Saver(new_checkpoint_vars)

with tf.Session() as sess:
   sess.run(init)
   saver.save(sess, NEW_CHECKPOINT_FILE)

python3文件读取问题，在im2text/run_reference.py中

将tf.gfile.gfile（文件名，“rb”）作为f:

从该链接下载的word_count.txt需要替换为此链接

---

在MacOS 10.13上，tf 1.4.1和python3.5的检查点文件也会出现同样的错误

原因：下载的检查点文件是使用旧版本的tensorflow（python2）生成的。word_count.txt文件格式

来自

变化： 1.生成可由tf1.4.1加载的ckp文件

OLD_CHECKPOINT_FILE = "model.ckpt-1000000"
NEW_CHECKPOINT_FILE = "model2.ckpt-1000000"

import tensorflow as tf
vars_to_rename = {
"lstm/basic_lstm_cell/weights": "lstm/basic_lstm_cell/kernel",
"lstm/basic_lstm_cell/biases": "lstm/basic_lstm_cell/bias",
}
new_checkpoint_vars = {}
reader = tf.train.NewCheckpointReader(OLD_CHECKPOINT_FILE)
for old_name in reader.get_variable_to_shape_map():
    if old_name in vars_to_rename:
        new_name = vars_to_rename[old_name]
else:
    new_name = old_name
new_checkpoint_vars[new_name] = 
tf.Variable(reader.get_tensor(old_name))`

init = tf.global_variables_initializer()
saver = tf.train.Saver(new_checkpoint_vars)

with tf.Session() as sess:
   sess.run(init)
   saver.save(sess, NEW_CHECKPOINT_FILE)

python3文件读取问题，在im2text/run_reference.py中

将tf.gfile.gfile（文件名，“rb”）作为f:

从该链接下载的word_count.txt需要替换为此链接

---

春芳的解决方案对我有效，但我想分享另一种方法

在TensorFlow的最新版本中，Google提供了一个“官方”实用程序来转换旧的RNN检查点：

python checkpoint_convert.py [--write_v1_checkpoint] \
  '/path/to/old_checkpoint' '/path/to/new_checkpoint'

---

春芳的解决方案对我有效，但我想分享另一种方法

在TensorFlow的最新版本中，Google提供了一个“官方”实用程序来转换旧的RNN检查点：

python checkpoint_convert.py [--write_v1_checkpoint] \
  '/path/to/old_checkpoint' '/path/to/new_checkpoint'