在Python中使用Keras和TensorFlow无法再现结果 [英] Results not reproducible with Keras and TensorFlow in Python

问题描述

我有问题，我无法使用Keras和ThensorFlow重现我的结果.

I have the problem, that I am not able to reproduce my results with Keras and ThensorFlow.

最近似乎在

It seems like recently there has been a workaround published on the Keras documentation site for this issue but somehow it doesn't work for me.

我做错了什么?

我正在MBP Retina上使用Jupyter笔记本(没有Nvidia GPU).

I'm using a Jupyter Notebook on a MBP Retina (without Nvidia GPU).

# ** Workaround from Keras Documentation **

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)


# ** Workaround end **

# ** Start of my code **


# LSTM and CNN for sequence classification in the IMDB dataset
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers.embeddings import Embedding
from keras.preprocessing import sequence
from sklearn import metrics
# fix random seed for reproducibility
#np.random.seed(7)

# ... importing data and so on ...

# create the model
embedding_vecor_length = 32
neurons = 91
epochs = 1
model = Sequential()
model.add(Embedding(top_words, embedding_vecor_length, input_length=max_review_length))
model.add(LSTM(neurons))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='mean_squared_logarithmic_error', optimizer='adam', metrics=['accuracy'])
print(model.summary())
model.fit(X_train, y_train, epochs=epochs, batch_size=64)
# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=0)
print("Accuracy: %.2f%%" % (scores[1]*100))

使用的Python版本:

Python 3.6.3 |Anaconda custom (x86_64)| (default, Oct  6 2017, 12:04:38) 
[GCC 4.2.1 Compatible Clang 4.0.1 (tags/RELEASE_401/final)]

该解决方法已包含在代码中(无效).

The workaround is already included in the code (without effect).

每次进行培训时，我都会得到不同的结果.

With everytime I do the training part I get different results.

重置Jupyter Notebook的内核时，第1次对应于第一次，第2次对应于第2次.

When resetting the kernel of the Jupyter Notebook, 1st time corresponds with the first time and 2nd time with 2nd time.

所以重置后，我总是会在第一次运行时得到0.7782，在第二次运行时总是得到0.7732，等等.

So after resetting I will always get for example 0.7782 at the first run, 0.7732 on the second run etc.

但是，每次运行内核时，未重置内核的结果总是不同的.

But results without kernel reset are always different each time I run it.

任何建议都会对我有帮助！

I would be helpful for any suggestion!

推荐答案

我遇到了完全相同的问题，并在每次运行模型时通过关闭并重新启动tensorflow会话设法解决了该问题.在您的情况下，它应如下所示:

I had exactly the same problem and managed to solve it by closing and restarting the tensorflow session every time I run the model. In your case it should look like this:

#START A NEW TF SESSION
np.random.seed(0)
tf.set_random_seed(0)
sess = tf.Session(graph=tf.get_default_graph())
K.set_session(sess)

embedding_vecor_length = 32
neurons = 91
epochs = 1
model = Sequential()
model.add(Embedding(top_words, embedding_vecor_length, input_length=max_review_length))
model.add(LSTM(neurons))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='mean_squared_logarithmic_error', optimizer='adam', metrics=['accuracy'])
print(model.summary())
model.fit(X_train, y_train, epochs=epochs, batch_size=64)
# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=0)
print("Accuracy: %.2f%%" % (scores[1]*100))

#CLOSE TF SESSION
K.clear_session()

我运行了以下代码，并使用GPU和tensorflow后端获得了可重现的结果:

I ran the following code and had reproducible results using GPU and tensorflow backend:

print datetime.now()
for i in range(10):
    np.random.seed(0)
    tf.set_random_seed(0)
    sess = tf.Session(graph=tf.get_default_graph())
    K.set_session(sess)

    n_classes = 3
    n_epochs = 20
    batch_size = 128

    task = Input(shape = x.shape[1:])
    h = Dense(100, activation='relu', name='shared')(task)
    h1= Dense(100, activation='relu', name='single1')(h)
    output1 = Dense(n_classes, activation='softmax')(h1)

    model = Model(task, output1)
    model.compile(loss='categorical_crossentropy', optimizer='Adam')
    model.fit(x_train, y_train_onehot, batch_size = batch_size, epochs=n_epochs, verbose=0)
print(model.evaluate(x=x_test, y=y_test_onehot, batch_size=batch_size, verbose=0))
K.clear_session()

并获得以下输出:

2017-10-23 11:27:14.494482
0.489712882132
0.489712893813
0.489712892765
0.489712854426
0.489712882132
0.489712864011
0.486303713004
0.489712903398
0.489712892765
0.489712903398

我了解的是，如果不关闭tf会话(通过在新内核中运行来完成)，您将继续采样相同的种子"分布.

What I understood is that if you don't close your tf session (you are doing it by running in a new kernel) you keep sampling the same "seeded" distribution.

这篇关于在Python中使用Keras和TensorFlow无法再现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！