Tensorflow 1.0之后模型文件、权重数值的读取

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')

你可能感兴趣的:(Tensorflow 1.0之后模型文件、权重数值的读取)