Question

我想在mnist数据集中预测我自己的测试数据的值但是我的代码总是返回相同的输出（2总是打印2）下面是我的代码我应该做些什么改变？

请帮助，提前致谢。

import sys
import tensorflow as tf
import cv2
import numpy as np
import scipy.ndimage
from PIL import Image,ImageFilter


# Define the model (same as when creating the model file)
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)

init_op = tf.initialize_all_variables()
saver = tf.train.Saver()
with tf.Session() as sess:
    sess.run(init_op)
    saver.restore(sess, "testdata/model.ckpt")
    print ("Model restored.")
    imvalue = cv2.imread("zero.jpg")
    gray_image = cv2.cvtColor(imvalue, cv2.COLOR_BGR2GRAY)
    #data = np.reshape(imvalue,[28,28])
    data = np.reshape(gray_image,-1)
    prediction=tf.argmax(y,1)
    pint=prediction.eval(feed_dict={x: [data]}, session=sess)

print (pint[0])`

预测您自己的测试图像上的mnist数据集的值

0 个答案: