【tf.keras】tf.keras模型复现

keras 构建模型很简单,上手很方便,同时又是 tensorflow 的高级 API,所以学学也挺好。

模型复现在我们的实验中也挺重要的,跑出了一个模型,虽然我们可以将模型的 checkpoint 保存,但再跑一遍,怎么都得不到相同的结果,对我而言这是不能接受的。

用 keras 实现模型,想要能够复现,需要将设置各个可能的随机过程的 seed;而且,代码不要在 GPU 上跑,而是在 CPU 上跑。(也就是说,GPU 上得到的 keras 模型没办法再复现。)

我的 tensorflow+keras 版本:

print(tf.VERSION)    # '1.10.0'
print(tf.keras.__version__)    # '2.1.6-tf'

keras 模型可复现的配置:

import numpy as np
import tensorflow as tf
import random as rn

import os
# run on CPU only
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
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://*.com/questions/42022950/

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)

# Rest of code follows ...

References

How can I obtain reproducible results using Keras during development? -- Keras Documentation
具有Tensorflow后端的Keras可以随意使用CPU或GPU吗?

上一篇:Program-Adaptive Mutational Fuzzing IEEE S&P(Oakland) 2015 论文解读


下一篇:javascript – 如何将单个文件指定为仅种子