Keras教程错误:NameError:未定义名称“ layers”

时间:2018-07-15 11:50:02

标签: python python-3.x tensorflow keras keras-layer

我正在尝试遵循this Keras教程,但是在使用命令import re pattern = re.compile(r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}') with open('test.txt', 'r') as rf: content = rf.read() matches = pattern.findall(content) open('iters.txt', 'w').close() for match in matches: with open('iters.txt', 'a') as wf: wf.write(match + '\n') 进行编译时遇到以下错误:

python3 test.py

我的代码如下:

Traceback (most recent call last):
  File "test.py", line 13, in <module>
    layers.Dense(64, activation='sigmoid')
NameError: name 'layers' is not defined

Python版本:

import tensorflow as tf
from tensorflow import keras

model = keras.Sequential()
# Adds a densely-connected layer with 64 units to the model:
model.add(keras.layers.Dense(64, activation='relu'))
# Add another:
model.add(keras.layers.Dense(64, activation='relu'))
# Add a softmax layer with 10 output units:
model.add(keras.layers.Dense(10, activation='softmax'))

# Create a sigmoid layer:
layers.Dense(64, activation='sigmoid')

# A linear layer with L1 regularization of factor 0.01 applied to the kernel matrix:
layers.Dense(64, kernel_regularizer=keras.regularizers.l1(0.01))
# A linear layer with L2 regularization of factor 0.01 applied to the bias vector:
layers.Dense(64, bias_regularizer=keras.regularizers.l2(0.01))

# A linear layer with a kernel initialized to a random orthogonal matrix:
layers.Dense(64, kernel_initializer='orthogonal')

操作系统:

MacOS High Sierra

我也在命令行Python 3.6.6 环境中完成所有操作。

如果人们可以抽出时间来帮助我,我将不胜感激。

1 个答案:

答案 0 :(得分:2)

怎么了

首先,python向您发出信号,表示脚本范围内不存在名称为layers的对象。

但是实际的错误是代码是从TensorFlow's Keras documentation中复制出来的,但是在文档中,代码的第二部分仅用于说明在model.add(...)调用中实例化的内容。 / p>

因此,请仅删除所有以layers开头的代码,这只是一个解释。

import tensorflow as tf
from tensorflow import keras

model = keras.Sequential()
# Adds a densely-connected layer with 64 units to the model:
model.add(keras.layers.Dense(64, activation='relu'))
# Add another:
model.add(keras.layers.Dense(64, activation='relu'))
# Add a softmax layer with 10 output units:
model.add(keras.layers.Dense(10, activation='softmax'))

更多读数

您应该考虑在Keras Documentation上了解 Keras

相关问题