当前位置:主页 > 软件编程 > Python代码 >

Tensorflow 1.0之后模型文件、权重数值的读取方式

时间:2021-06-27 08:23:17 | 栏目:Python代码 | 点击:

保存的文件有4个:

checkpoint

model-parameters.bin-46000.data-00000-of-00001

model-parameters.bin-46000.index

model-parameters.bin-46000.meta

读取代码:

from tensorflow.python import pywrap_tensorflow

with tf.Graph().as_default(): 
 with tf.Session() as sess:
 ckpt = tf.train.get_checkpoint_state('./checkpoint')
 if ckpt and ckpt.model_checkpoint_path:
  reader = pywrap_tensorflow.NewCheckpointReader('./checkpoint/model-parameters.bin-46000')
  all_variables = reader.get_variable_to_shape_map()
  w1 = reader.get_tensor("conv1/weight")
  print(w1.shape)
  print(w1)
  print(all_variables)
 else:
  print('No checkpoint file found')

您可能感兴趣的文章:

相关文章