save-model

# Image Tensor
images_placeholder = tf.placeholder(tf.float32, shape=[None, 32, 32, 3], name='x')

gray = tf.image.rgb_to_grayscale(images_placeholder, name='gray')

gray /= 255.

# Label Tensor
labels_placeholder = tf.placeholder(tf.float32, shape=(None, 43), name='y')

# dropout Tensor
keep_prob = tf.placeholder(tf.float32, name='drop')

# construct model
logits = inference(gray, keep_prob)

# calculate loss
loss_value = loss(logits, labels_placeholder)

# training
train_op = training(loss_value, 0.001)

# accuracy
acc = accuracy(logits, labels_placeholder)


sess = tf.Session()

sess.run(tf.initialize_all_variables())

# for TensorBoard
summary_op = tf.merge_all_summaries()

summary_writer = tf.train.SummaryWriter("/home/ubuntu", sess.graph)

with tf.Session() as sess:
    sess.run(tf.initialize_all_variables())
    num_examples = len(X_train)
    
    print("Training...")
    print()
    for i in range(EPOCHS):
        for j in range(steps):
            # train for batch_size
            batch_x, batch_y = next_batch(X_train, Y_train, BATCH_SIZE)
            sess.run(train_op, feed_dict={
                images_placeholder: batch_x,
                labels_placeholder: batch_y,
                keep_prob: 0.5})
            
        val_accuracy, val_loss = evaluate(X_val, Y_val)
        if i % 10 == 0:
            print("EPOCH {} ...".format(i+1))
            print("Validation Loss = {:.3f} and Validation Accuracy = {:.3f}".format(val_loss, val_accuracy*100))
            print()
        
        if val_accuracy > .93:
            break
        
    try:
        saver
    except NameError:
        saver = tf.train.Saver()
    saver.save(sess, 'gtsd')
    print("Model saved")