Google Colab上的Tensorflow-Keras可再现性问题 [英] Tensorflow-Keras reproducibility problem on Google Colab

问题描述

我有一个简单的代码可以在Google Colab上运行(我使用CPU模式):

I have a simple code to run on Google Colab (I use CPU mode):

import numpy as np
import pandas as pd

## LOAD DATASET

datatrain = pd.read_csv("gdrive/My Drive/iris_train.csv").values
xtrain = datatrain[:,:-1]
ytrain = datatrain[:,-1]

datatest = pd.read_csv("gdrive/My Drive/iris_test.csv").values
xtest = datatest[:,:-1]
ytest = datatest[:,-1]

import tensorflow as tf
from tensorflow.keras.layers import Dense, Activation
from tensorflow.keras.utils import to_categorical

## SET ALL SEED

import os
os.environ['PYTHONHASHSEED']=str(66)

import random
random.seed(66)

np.random.seed(66)
tf.set_random_seed(66)

from tensorflow.keras import backend as K
session_conf = tf.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1)
sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)
K.set_session(sess)

## MAIN PROGRAM

ycat = to_categorical(ytrain) 

# build model
model = tf.keras.Sequential()
model.add(Dense(10, input_shape=(4,)))
model.add(Activation("sigmoid"))
model.add(Dense(3))
model.add(Activation("softmax"))

#choose optimizer and loss function
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])

# train
model.fit(xtrain, ycat, epochs=15, batch_size=32)

#get prediction
classes = model.predict_classes(xtest)

#get accuration
accuration = np.sum(classes == ytest)/len(ytest) * 100

我已在此处阅读了用于创建可重复性代码的设置使用带有TensorFlow后端的Keras的可重复结果，我将所有代码都放入了在同一单元格中.但是每次运行该单元格(使用shift + enter运行该单元格)时，结果(例如损失)总是不同的.

I have read the setup to create a reproducibility code here Reproducible results using Keras with TensorFlow backend and I put all code in the same cell. But the result (e.g. the loss) is always different every time I run that cell (run the cell using shift + enter).

就我而言，如果只有以下情况，则可以复制上面代码的结果:

In my case, the result from the code above can be reproduced, if only:

1. 我使用运行时">重新启动并全部运行"运行，或者
2. 我将该代码放在一个文件中，然后使用命令行(python3 file.py)运行它

1. I run using "runtime" > "restart and run all" or,
2. I put that code in a single file and run it using the command line (python3 file.py)

我想念些什么来使结果可重现而不重新启动运行时吗?

is there something I miss to make the result reproducible without restart the runtime?

推荐答案

您还应该在Dense层中修复kernel_initializer的种子.因此，您的模型将如下所示:

You should also fix the seed for kernel_initializer in your Dense layers. So, your model will be like:

model = tf.keras.Sequential()
model.add(Dense(10, kernel_initializer=keras.initializers.glorot_uniform(seed=66), input_shape=(4,)))
model.add(Activation("sigmoid"))
model.add(Dense(3, kernel_initializer=keras.initializers.glorot_uniform(seed=66)))
model.add(Activation("softmax"))

这篇关于Google Colab上的Tensorflow-Keras可再现性问题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！