【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。

用 keras 实现模型，想要能够复现，首先需要设置各个可能的随机过程的 seed，如 np.random.seed(1)。然后分为两种情况：

1. 代码不要在 GPU 上跑，而是限制在 CPU 上跑，此时可以自行设置 fit 函数的 batch_size 参数；
2. 代码可以在 GPU 上跑，需要设置 fit 函数的参数 batch_size = 1。（当使用 tf.keras.conv2D() 时，似乎在 GPU 上跑没法复现，最好使用第一种方式，只在 CPU 上跑。）

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, if you want to run code on GPU, you should delete the following line.
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://stackoverflow.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 ...

对于 tensorflow low-level API，即用 tf.variable_scope() 和 tf.get_variable() 自行构建 layers，同样会出现这种问题。

keras 文档 对此的解释是：

Moreover, when using the TensorFlow backend and running on a GPU, some operations have non-deterministic outputs, in particular tf.reduce_sum(). This is due to the fact that GPUs run many operations in parallel, so the order of execution is not always guaranteed. Due to the limited precision of floats, even adding several numbers together may give slightly different results depending on the order in which you add them. You can try to avoid the non-deterministic operations, but some may be created automatically by TensorFlow to compute the gradients, so it is much simpler to just run the code on the CPU.

而 pytorch 是怎么保证可复现：（cudnn中对卷积操作进行了优化，牺牲了精度来换取计算效率。可以看到，下面的代码强制 cudnn 产生确定性的结果，但会牺牲效率。具体参见博客 PyTorch的可重复性问题 （如何使实验结果可复现））

from torch.backends import cudnn
cudnn.benchmark = False            # if benchmark=True, deterministic will be False
cudnn.deterministic = True

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？
PyTorch的可重复性问题 （如何使实验结果可复现）-- hyk_1996

转载于:https://www.cnblogs.com/wuliytTaotao/p/10883749.html