python - MNIST tensorflow tutorial -

i trying extend mnist tensorflow tutorial 'deep learning experts' trying print final value of y_conv (from tutorial), here code :

with sess.as_default():     x_test=mnist.test.images[10]     x_test=np.reshape(x_test,(-1,784))     print(y_conv.eval(feed_dict={x:x_test,keep_prob:1}))     print (accuracy.eval(feed_dict={x: np.reshape(mnist.test.images[10],-1,784) 

i getting weird value y_conv :

[[ 18.27762222 -3.28520679 2.48342848 -4.64049053 -6.00347185
-4.08683825 -1.80674195 -2.16284728 -4.48559856 1.90175676]]

although when printing accuracy in last line, getting value of 1.0, means y_conv matching value of y (again tutorial.) ideas on going wrong..?

you aren't printing y_conv activation function applied. if apply softmax function, you'll see it'll like:

[[1, 0, 0.7ish, 0, 0, 0, 0.3ish, 0.2ish, 0, 0.7ish]] 

try applying activation , see get.