Tensorflow passing image to simple MNIST Data Model - tensorflow

Question

I have simple model for MNIST data classification with accuracy around 92%.
I would like to know if there is any way I can provide image with digit and get label as output for that digit ? Image can be from mnist test data, rather than custom image, just to avoid image preprocessing? Below is code for my model.
Thanks
import tensorflow as tf
#reset graph
tf.reset_default_graph()
#constants
learning_rate = 0.5
batch_size = 100
training_epochs = 5
logs_path = "/tmp/mnist/2"
#load mnist data set
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
with tf.name_scope('inputs'):
x = tf.placeholder(tf.float32, shape=[None,784], name = "image-input")
y_= tf.placeholder(tf.float32, shape=[None, 10], name = "labels-input")
#weights
with tf.name_scope("weights"):
W = tf.Variable(tf.zeros([784,10]))
#biases
with tf.name_scope("biases"):
b= tf.Variable(tf.zeros([10]))
#Activation function softmax
with tf.name_scope("softmax"):
#y is prediction
y = tf.nn.softmax(tf.matmul(x,W) +b)
#Cost function
with tf.name_scope('cross_entropy'):
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y),reduction_indices=[1])) #????
#Define Optimizer
with tf.name_scope('train'):
train_optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cross_entropy)
#Accuracy
with tf.name_scope('Accuracy'):
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
tf.summary.scalar("cost",cross_entropy)
tf.summary.scalar("accuracy",accuracy)
#Merge all summaries into a single "operation" which will be executed in a session
summary_op = tf.summary.merge_all()
with tf.Session() as sess:
#initialize variables before using them
sess.run(tf.global_variables_initializer())
#log writer object
# writer = tf.train.SummaryWriter(logs_path, graph=tf.get_default_graph())
writer = tf.summary.FileWriter(logs_path,graph=tf.get_default_graph())
#training cycles
for epoch in range(training_epochs):
#number of batches in one epoch
batch_count = int(mnist.train.num_examples/batch_size)
for i in range(batch_count):
batch_x, batch_y = mnist.train.next_batch(batch_size)
_,summary = sess.run([train_optimizer,summary_op], feed_dict={x: batch_x, y_:batch_y})
writer.add_summary(summary,epoch * batch_count + i)
if epoch % 5 == 0:
print("Epoch: ",epoch)
print("Accuracy: ",accuracy.eval(feed_dict={x: mnist.test.images,y_:mnist.test.labels}))
print("Done")

Answer 1

After you trained the network, you can get the label that the network gives to a new image by doing
new_image_label= sess.run(y, feed_dict={x: new_image})
Note that the format of new_image should be the same as of batch_x. Think about new_image as a batch of size 1, so if batch_x is 2D, new_image should also be 2D (of shape 1 by 784).
In addition, if you did some pre-processing (like normalization for example) to the images in batch_x, you need to do the same thing with new_image.
You could also get the labels of several images simultaneously with the same code as above. Just replace new_image with some 2D array of several images new_images.