Tensorflow: 读取ckpt文件中的tensor

在使用pre-train model时候,我们需要restore variables from checkpoint files.
经常出现在checkpoint 中找不到”Tensor name not found”.
这时候需要查看一下ckpt中到底有哪些变量

import os
from tensorflow.python import pywrap_tensorflow

model_dir="./"

checkpoint_path = os.path.join(model_dir, "resnet_v2_152.ckpt")
# Read data from checkpoint file
reader = pywrap_tensorflow.NewCheckpointReader(checkpoint_path)
var_to_shape_map = reader.get_variable_to_shape_map()
# Print tensor name and values
for key in var_to_shape_map:
    print("tensor_name: ", key)
    print(reader.get_tensor(key))

转自:http://blog.csdn.net/noirblack/article/details/71430790

猜你喜欢

转载自blog.csdn.net/zw__chen/article/details/81064977