[Python] How to use the saved model in tensorflow [duplicate]

First, I tried to restore the model as people instructed, but I could not find any clues yet. Following is my code to save the model and model was successfully saved.

import tensorflow as tf
from sklearn.utils import shuffle
EPOCHS = 10
BATCH_SIZE = 128

x = tf.placeholder(tf.float32, (None, 32, 32, 3),name='x')
y = tf.placeholder(tf.int32, (None),name='y')
one_hot_y = tf.one_hot(y, 43)

rate = 0.001

logits = LeNet(x)
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=one_hot_y, logits=logits)
loss_operation = tf.reduce_mean(cross_entropy)
optimizer = tf.train.AdamOptimizer(learning_rate = rate)
training_operation = optimizer.minimize(loss_operation)

correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(one_hot_y, 1))
accuracy_operation = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
saver = tf.train.Saver()

def evaluate(TrainX, trainLabels):
num_examples = len(TrainX)
total_accuracy = 0
sess = tf.get_default_session()
for offset in range(0, num_examples, BATCH_SIZE):
batch_x, batch_y = TrainX[offsetffset+BATCH_SIZE], trainLabels[offsetffset+BATCH_SIZE]
accuracy = sess.run(accuracy_operation, feed_dict={x: batch_x, y: batch_y})
total_accuracy += (accuracy * len(batch_x))
return total_accuracy / num_examples

with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
num_examples = len(trainImages)

print("Training...")
print()
for i in range(EPOCHS):
TrainX, trainLabels = shuffle(TrainX, trainLabels)
for offset in range(0, num_examples, BATCH_SIZE):
end = offset + BATCH_SIZE
batch_x, batch_y = TrainX[offset:end], trainLabels[offset:end]
sess.run(training_operation, feed_dict={x: batch_x, y: batch_y})

validation_accuracy = evaluate(TrainX, trainLabels)
print("EPOCH {} ...".format(i+1))
print("Validation Accuracy = {:.3f}".format(validation_accuracy))
print()

saver.save(sess, './lenet')
print("Model saved")


Training...

EPOCH 1 ... Validation Accuracy = 0.765

EPOCH 2 ... Validation Accuracy = 0.911

EPOCH 3 ... Validation Accuracy = 0.933

EPOCH 4 ... Validation Accuracy = 0.958

EPOCH 5 ... Validation Accuracy = 0.965

EPOCH 6 ... Validation Accuracy = 0.973

EPOCH 7 ... Validation Accuracy = 0.978

EPOCH 8 ... Validation Accuracy = 0.986

EPOCH 9 ... Validation Accuracy = 0.985

EPOCH 10 ... Validation Accuracy = 0.980

Model saved

My question is how I can use this model when I put new test data supposing that I put 5 test data to see how accurate they are when passing through in the trained model. I'd like to see the accuracy of test data and labels which will correctly fit in the trained model. Thank you for your time and I am willing to give you more details if you have things you do not understand.

Continue reading...