在Tensorflow后端运行Keras时如何获得可重现的结果 [英] How to get reproducible result when running Keras with Tensorflow backend
问题描述
每次我在jupyter笔记本中使用Keras运行LSTM网络时，都会得到不同的结果，并且我在Google上搜索了很多，并且尝试了一些不同的解决方案，但是它们都不起作用，下面是我尝试过的一些解决方案:
Every time I run LSTM network with Keras in jupyter notebook, I got a different result, and I have googled a lot, and I have tried some different solutions, but none of they are work, here are some solutions I tried:
-
设置numpy随机种子
set numpy random seed
random_seed=2017
from numpy.random import seed
seed(random_seed)
random_seed=2017
from numpy.random import seed
seed(random_seed)
设置张量流随机种子
from tensorflow import set_random_seed
set_random_seed(random_seed)
from tensorflow import set_random_seed
set_random_seed(random_seed)
设置内置随机种子
import random
random.seed(random_seed)
import random
random.seed(random_seed)
设置PYTHONHASHSEED
set PYTHONHASHSEED
import os
os.environ['PYTHONHASHSEED'] = '0'
import os
os.environ['PYTHONHASHSEED'] = '0'
在jupyter笔记本kernel.json中添加PYTHONHASHSEED
add PYTHONHASHSEED in jupyter notebook kernel.json
{
"language": "python",
"display_name": "Python 3",
"env": {"PYTHONHASHSEED": "0"},
"argv": [
"python",
"-m",
"ipykernel_launcher",
"-f",
"{connection_file}"
]
}
{
"language": "python",
"display_name": "Python 3",
"env": {"PYTHONHASHSEED": "0"},
"argv": [
"python",
"-m",
"ipykernel_launcher",
"-f",
"{connection_file}"
]
}
而我的环境版本是:
Keras: 2.0.6
Tensorflow: 1.2.1
CPU or GPU: CPU
这是我的代码:
model = Sequential()
model.add(LSTM(16, input_shape=(time_steps,nb_features), return_sequences=True))
model.add(LSTM(16, input_shape=(time_steps,nb_features), return_sequences=False))
model.add(Dense(8,activation='relu'))
model.add(Dense(1,activation='linear'))
model.compile(loss='mse',optimizer='adam')
推荐答案
您的模型定义中肯定缺少种子.可以在这里找到详细的文档: https://keras.io/initializers/.
The seed is definitely missing from your model definition. A detailed documentation can be found here: https://keras.io/initializers/.
从本质上讲，您的图层使用随机变量作为其参数的基础.因此，您每次都会获得不同的输出.
In essence your layers use random variables as their basis for their parameters. Therefore you get different outputs every time.
一个例子:
model.add(Dense(1, activation='linear',
kernel_initializer=keras.initializers.RandomNormal(seed=1337),
bias_initializer=keras.initializers.Constant(value=0.1))
Keras本身在常见问题解答"部分中提供了有关获得可再现结果的部分:(
Keras themselves have a section about getting reproduceable results in their FAQ section: (https://keras.io/getting-started/faq/#how-can-i-obtain-reproducible-results-using-keras-during-development). They have the following code snippet to produce reproducable results:
import numpy as np
import tensorflow as tf
import random as rn
# The below is necessary in Python 3.2.3 onwards to
# have reproducible behavior for certain hash-based operations.
# See these references for further details:
# https://docs.python.org/3.4/using/cmdline.html#envvar-PYTHONHASHSEED
# https://github.com/fchollet/keras/issues/2280#issuecomment-306959926
import os
os.environ['PYTHONHASHSEED'] = '0'
# The below is necessary for starting Numpy generated random numbers
# in a well-defined initial state.
np.random.seed(42)
# The below is necessary for starting core Python generated random numbers
# in a well-defined state.
rn.seed(12345)
# Force TensorFlow to use single thread.
# Multiple threads are a potential source of
# non-reproducible results.
# For further details, see: https://stackoverflow.com/questions/42022950/which-seeds-have-to-be-set-where-to-realize-100-reproducibility-of-training-res
session_conf = tf.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1)
from keras import backend as K
# The below tf.set_random_seed() will make random number generation
# in the TensorFlow backend have a well-defined initial state.
# For further details, see: https://www.tensorflow.org/api_docs/python/tf/set_random_seed
tf.set_random_seed(1234)
sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)
K.set_session(sess)
这篇关于在Tensorflow后端运行Keras时如何获得可重现的结果的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
