我正在使用Tensorflow 0.8.0和Python v2.7。 我的IDE是PyCharm，我的操作系统是Linux Ubuntu 14.04
我注意到以下代码导致我的计算机冻结和/或崩溃：
# you will need these files!
# https://www.kaggle.com/c/digit-recognizer/download/train.csv
# https://www.kaggle.com/c/digit-recognizer/download/test.csv
import numpy as np
import pandas as pd
import tensorflow as tf
import matplotlib.pyplot as plt
import matplotlib.cm as cm
# read in the image data from the csv file
# the format is: imagelabel pixel0 pixel1 ... pixel783 (there are 42,000 rows like this)
data = pd.read_csv('../train.csv')
labels = data.iloc[:,:1].values.ravel() # shape = (42000, 1)
labels_count = np.unique(labels).shape[0] # = 10
images = data.iloc[:,1:].values # shape = (42000, 784)
images = images.astype(np.float64)
image_size = images.shape[1]
image_width = image_height = np.sqrt(image_size).astype(np.int32) # since these images are sqaure... hieght = width
# turn all the gray-pixel image-values into percentages of 255
# a 1.0 means a pixel is 100% black, and 0.0 would be a pixel that is 0% black (or white)
images = np.multiply(images, 1.0/255)
# create oneHot vectors from the label #s
oneHots = tf.one_hot(labels, labels_count, 1, 0) #shape = (42000, 10)
#split up the training data even more (into validation and train subsets)
VALIDATION_SIZE = 3167
validationImages = images[:VALIDATION_SIZE]
validationLabels = labels[:VALIDATION_SIZE]
trainImages = images[VALIDATION_SIZE:]
trainLabels = labels[VALIDATION_SIZE:]
# ------------- Building the NN -----------------
# set up our weights (or kernals?) and biases for each pixel
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(.1, shape=shape, dtype=tf.float32)
return tf.Variable(initial)
# convolution
def conv2d(x, W):
return tf.nn.conv2d(x, W, [1,1,1,1], 'SAME')
# pooling
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
# placeholder variables
# images
x = tf.placeholder('float', shape=[None, image_size])
# labels
y_ = tf.placeholder('float', shape=[None, labels_count])
# first convolutional layer
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
# turn shape(40000,784) into (40000,28,28,1)
image = tf.reshape(trainImages, [-1,image_width , image_height,1])
image = tf.cast(image, tf.float32)
# print (image.get_shape()) # =>(40000,28,28,1)
h_conv1 = tf.nn.relu(conv2d(image, W_conv1) + b_conv1)
# print (h_conv1.get_shape()) # => (40000, 28, 28, 32)
h_pool1 = max_pool_2x2(h_conv1)
# print (h_pool1.get_shape()) # => (40000, 14, 14, 32)
# second convolutional layer
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
#print (h_conv2.get_shape()) # => (40000, 14,14, 64)
h_pool2 = max_pool_2x2(h_conv2)
#print (h_pool2.get_shape()) # => (40000, 7, 7, 64)
# densely connected layer
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
# (40000, 7, 7, 64) => (40000, 3136)
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
#print (h_fc1.get_shape()) # => (40000, 1024)
# dropout
keep_prob = tf.placeholder('float')
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
print h_fc1_drop.get_shape()
#readout layer for deep neural net
W_fc2 = weight_variable([1024,labels_count])
b_fc2 = bias_variable([labels_count])
print b_fc2.get_shape()
mull= tf.matmul(h_fc1_drop, W_fc2)
print mull.get_shape()
print
mull2 = mull + b_fc2
print mull2.get_shape()
y = tf.nn.softmax(mull2)
# dropout
keep_prob = tf.placeholder('float')
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
sess = tf.Session()
sess.run(tf.initialize_all_variables())
print sess.run(mull[0,2])
拉塞线导致崩溃：
print sess.run(mull[0,2])
这基本上是一个非常大的2D阵列中的一个位置。 关于sess.run的一些事情导致了它。 我还收到一个脚本问题弹出窗口...某种谷歌脚本(认为也许是TensorFlow？)。 我无法复制链接，因为我的计算机完全冻结了。
我怀疑问题之所以出现，是因为mull[0, 2]尽管它的表观尺寸很小，但它依赖于非常大的计算，包括多个卷积、最大池化和大矩阵乘法;因此，您的计算机长时间完全加载，或者内存不足。(您应该能够通过运行top并检查运行 TensorFlow 的python进程使用了哪些资源来判断哪些资源。
计算量如此之大，是因为您的 TensorFlow 图是根据包含 40000 张图像的整个训练数据集trainImages定义的
image = tf.reshape(trainImages, [-1,image_width , image_height,1])
image = tf.cast(image, tf.float32)
相反，根据可以向其提供单个训练示例或小批量示例的tf.placeholder()来定义您的网络会更有效。有关详细信息，请参阅有关喂养的文档。特别是，由于您只对第 0 行mull感兴趣，因此您只需从trainImages中馈送第 0 个示例并对其执行计算以生成必要的值。(在当前程序中，还会计算所有其他示例的结果，然后在最终切片运算符中丢弃。
将会话设置为默认值，并在运行会话之前初始化变量可能会解决您的问题。
import tensorflow as tf
sess = tf.Session()
g = tf.ones([25088])
sess.as_default():
tf.initialize_all_variables().run()
results = sess.run(g)
print results