问题描述
我正在尝试编写一个脚本,该脚本将允许我绘制一个数字的图像,然后使用在MNIST上训练的模型来确定它是哪个数字.
I'm trying to write a script that will allow me to draw an image of a digit and then determine what digit it is with a model trained on MNIST.
这是我的代码:
import random
import image
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
import numpy as np
import scipy.ndimage
mnist = input_data.read_data_sets( "MNIST_data/", one_hot=True )
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x, W) + b)
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize (cross_entropy)
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
for i in range( 1000 ):
batch_xs, batch_ys = mnist.train.next_batch( 1000 )
sess.run(train_step, feed_dict= {x: batch_xs, y_: batch_ys})
print ("done with training")
data = np.ndarray.flatten(scipy.ndimage.imread("im_01.jpg", flatten=True))
result = sess.run(tf.argmax(y,1), feed_dict={x: [data]})
print (' '.join(map(str, result)))
由于某种原因,结果总是错误的,但是当我使用标准测试方法时,其准确率达到92%.
For some reason the results are always wrong but has a 92% accuracy when I use the standard testing method.
我认为问题可能在于我如何编码图像:
I think the problem might be how I encoded the image:
data = np.ndarray.flatten(scipy.ndimage.imread("im_01.jpg", flatten=True))
我尝试在tensorflow代码中查找 next_batch()函数看看他们是如何做到的,但是我不知道该如何与我的方法进行比较.
I tried looking in the tensorflow code for the next_batch() function to see how they did it, but I have no idea how I can compare against my approach.
问题也可能在其他地方.
The problem might be somewhere else too.
对于将准确性提高到80%以上的任何帮助,我们将不胜感激.
Any help to make the accuracy 80+% would be greatly appreciated.
推荐答案
我发现了我的错误:它编码了相反的字符,黑人是255,而不是0.
I found my mistake: it encoded the reverse, blacks were at 255 instead of 0.
data = np.vectorize(lambda x: 255 - x)(np.ndarray.flatten(scipy.ndimage.imread("im_01.jpg", flatten=True)))
解决了.
这篇关于Tensorflow-用我自己的图像测试mnist神经网络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!