Revision history [back]

Predict wrong number using CNN model

Hello

OpenCV 3.4.1

Python 3.6

Tensorflow 1.5.0

There is CNN LeNet sample code and train 99% accuracy.

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets('MNIST_data/', one_hot = True) 

sess = tf.InteractiveSession()  

def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev = 0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial = tf.constant(0.1, shape = shape)
    return tf.Variable(initial)

def conv2d(x,W):
    return tf.nn.conv2d(x, W, strides = [1, 1, 1, 1], padding ='SAME')

def max_pool_2x2(x):    
    return tf.nn.max_pool(x, ksize = [1, 2, 2, 1], strides = [1, 2, 2, 1],padding='SAME')


x = tf.placeholder(tf.float32, [None, 784], name='input') 
x_image = tf.reshape(x, [-1,28,28,1]) 

W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)         
h_pool1 = max_pool_2x2(h_conv1)

W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)             
h_pool2 = max_pool_2x2(h_conv2)

W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])   
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1, W_fc2) + b_fc2, name='softmax')

tf.train.write_graph(sess.graph_def, './save_folder/', 'graph.pbtxt', as_text=True)

tf.train.write_graph(sess.graph_def, './save_folder/', 'graph.pb', as_text=False)

y_ = tf.placeholder(tf.float32, [None, 10])

cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices = [1]))  
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

tf.global_variables_initializer().run()

saver = tf.train.Saver()
for i in range(1000):
    batch = mnist.train.next_batch(100)
    if i%100 ==0:
        train_accuracy = accuracy.eval(feed_dict= {x: batch[0], y_: batch[1]})
        print('step %d, training accuracy %g' %(i, train_accuracy))
    train_step.run(feed_dict={x: batch[0], y_: batch[1]})    

saver.save(sess, "./save_folder/model.ckpt")

But when I applied this model in opencv using c++, it predicted almost wrong in mnist test dataset.

Below link is test number image as jpg file. https://drive.google.com/file/d/1KJKslgCcxf6QSO0VPwCc6qXnY3Fw2AC8/view?usp=sharing

Below link is .pb file combined with .ckpt and graph. https://drive.google.com/file/d/1NAhUJsAObq_z6IUTX9Tg9y3yMuX7FFcl/view?usp=sharing

Thanks