I've adjusted the data loading of the TensorFlow MNIST example to use the original MNIST data. The original example gets > 0.80 accuracy after 100 epochs. My adjusted example (set use_original = False to use it) gets only about 0.09 - 0.10 accuracy (which is just random). Could you please explain why?
#!/usr/bin/env python
"""MNIST with Tensorflow."""
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
from struct import unpack
import gzip
from numpy import zeros, uint8
from sklearn.preprocessing import OneHotEncoder
use_original = True
def get_labeled_data(imagefile, labelfile):
"""
Read input-vector (image) and target class (label, 0-9).
Return
------
tuple of lists
"""
# Open the images with gzip in read binary mode
images = gzip.open(imagefile, 'rb')
labels = gzip.open(labelfile, 'rb')
# Read the binary data
# We have to get big endian unsigned int. So we need '>I'
# Get metadata for images
images.read(4) # skip the magic_number
number_of_images = images.read(4)
number_of_images = unpack('>I', number_of_images)[0]
rows = images.read(4)
rows = unpack('>I', rows)[0]
cols = images.read(4)
cols = unpack('>I', cols)[0]
# Get metadata for labels
labels.read(4) # skip the magic_number
N = labels.read(4)
N = unpack('>I', N)[0]
if number_of_images != N:
raise Exception('number of labels did not match the number of images')
# Get the data
x = zeros((N, rows * cols), dtype=uint8) # Initialize numpy array
y = zeros((N, 1), dtype=uint8) # Initialize numpy array
for i in range(N):
if i % 1000 == 0:
print("%s: %i" % (imagefile, i))
j = 0
for row in range(rows):
for col in range(cols):
tmp_pixel = images.read(1) # Just a single byte
tmp_pixel = unpack('>B', tmp_pixel)[0]
x[i][j] = tmp_pixel
j += 1
tmp_label = labels.read(1)
y[i] = unpack('>B', tmp_label)[0]
enc = OneHotEncoder()
enc.fit(y)
y = enc.transform(y).toarray()
return (x, y)
epochs = 20000
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')
def eval_network(dataset, correct_prediction):
correct_sum = 0
total_test = 0
for i in range(dataset.labels.shape[0] / 1000):
feed_dict = {x: dataset.images[i * 1000:(i + 1) * 1000],
y_: dataset.labels[i * 1000:(i + 1) * 1000],
keep_prob: 1.0}
test_correct = correct_prediction.eval(feed_dict=feed_dict)
correct_sum += sum(test_correct)
total_test += len(test_correct)
return float(correct_sum) / total_test
def add_score(filename, mnist, scoring, epoch, other=''):
with open(filename, "a") as myfile:
train = eval_network(mnist.train, scoring)
test = eval_network(mnist.test, scoring)
myfile.write("%i;%0.6f;%0.6f;%s\n" % (epoch, train, test, other))
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
sess = tf.InteractiveSession()
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
sess.run(tf.initialize_all_variables())
y = tf.nn.softmax(tf.matmul(x, W) + b)
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1, 28, 28, 1])
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)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
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))
sess.run(tf.initialize_all_variables())
# Data loading
if use_original:
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
else:
mnist = lambda: None
setattr(mnist, 'train', lambda: None)
setattr(mnist, 'test', lambda: None)
setattr(mnist.train, 'images', lambda: None)
setattr(mnist.train, 'labels', lambda: None)
setattr(mnist.test, 'images', lambda: None)
setattr(mnist.test, 'labels', lambda: None)
xs, ys = get_labeled_data('mnist/train-images-idx3-ubyte.gz',
'mnist/train-labels-idx1-ubyte.gz')
mnist.train.images = xs
mnist.train.labels = ys
xst, yst = get_labeled_data('mnist/t10k-images-idx3-ubyte.gz',
'mnist/t10k-labels-idx1-ubyte.gz')
mnist.test.images = xst
mnist.test.labels = yst
for i in range(epochs):
if use_original:
batch = mnist.train.next_batch(50) # This works
else:
# This doesnt work
batch = (xs[i * 50:(i + 1) * 50], ys[i * 50:(i + 1) * 50])
if i % 100 == 0:
add_score('accuracy.csv',
mnist,
correct_prediction,
i)
train_step.run(feed_dict={x: batch[0],
y_: batch[1],
keep_prob: 0.5})
add_score('accuracy.csv', mnist, correct_prediction, epochs)
I found the problem. The data needs to be loaded as numpy.float32 (and normalized by dividing it through 255).