我在mac osx上用keras训练mobilenet的虚拟数据架构。我两个都订好了
nump.random
和
tensorflow.set_random_seed
,但由于某些原因,我无法获得可重复的结果:每次重新运行代码时,我都会得到不同的结果。为什么?这不是因为GPU,因为我运行的MacBook Pro 2017带有Radeon图形卡,因此TensorFlow没有利用它。代码是用
python Keras_test.py
所以这不是状态问题(我没有使用jupyter或ipython:每次运行代码时都应该重置环境)。
编辑
:我通过移动所有种子的设置来更改代码
之前
正在导入Keras。结果仍不确定,但结果的方差比以前小得多。这很奇怪。
目前的模型非常小(就深度神经网络而言),不需要繁琐,它不需要GPU运行,在现代笔记本电脑上几分钟就可以训练,所以重复我的实验是任何人都可以做到的。我邀请你这么做:我很想了解一个系统到另一个系统的变化程度。
import numpy as np
# random seeds must be set before importing keras & tensorflow
my_seed = 512
np.random.seed(my_seed)
import random
random.seed(my_seed)
import tensorflow as tf
tf.set_random_seed(my_seed)
# now we can import keras
import keras.utils
from keras.applications import MobileNet
from keras.callbacks import ModelCheckpoint
from keras.optimizers import Adam
import os
height = 224
width = 224
channels = 3
epochs = 10
num_classes = 10
# Generate dummy data
batch_size = 32
n_train = 256
n_test = 64
x_train = np.random.random((n_train, height, width, channels))
y_train = keras.utils.to_categorical(np.random.randint(num_classes, size=(n_train, 1)), num_classes=num_classes)
x_test = np.random.random((n_test, height, width, channels))
y_test = keras.utils.to_categorical(np.random.randint(num_classes, size=(n_test, 1)), num_classes=num_classes)
# Get input shape
input_shape = x_train.shape[1:]
# Instantiate model
model = MobileNet(weights=None,
input_shape=input_shape,
classes=num_classes)
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
# Viewing Model Configuration
model.summary()
# Model file name
filepath = 'model_epoch_{epoch:02d}_loss_{loss:0.2f}_val_{val_loss:.2f}.hdf5'
# Define save_best_only checkpointer
checkpointer = ModelCheckpoint(filepath=filepath,
monitor='val_acc',
verbose=1,
save_best_only=True)
# Let's fit!
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
validation_data=(x_test, y_test),
callbacks=[checkpointer])
一如既往,这里是我的python,keras&tensorflow版本:
python -c 'import keras; import tensorflow; import sys; print(sys.version, 'keras.__version__', 'tensorflow.__version__')'
/anaconda2/lib/python2.7/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
Using TensorFlow backend.
('2.7.15 |Anaconda, Inc.| (default, May 1 2018, 18:37:05) \n[GCC 4.2.1 Compatible Clang 4.0.1 (tags/RELEASE_401/final)]', '2.1.6', '1.8.0')
下面是多次运行此代码获得的一些结果:如您所见,代码使用描述性文件名保存了10个阶段中的最佳模型(最佳验证精度),因此通过比较不同运行中的文件名可以判断结果的可变性。
model_epoch_01_loss_2.39_val_3.28.hdf5
model_epoch_01_loss_2.39_val_3.54.hdf5
model_epoch_01_loss_2.40_val_3.47.hdf5
model_epoch_01_loss_2.41_val_3.08.hdf5
