test1.py

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import pandas as pd
import tensorflow as tf
import numpy as np

VALIDATION_SIZE = 2000
BATCH_SIZE = 50


def dense_to_one_hot(labels_dense, num_classes):
    num_labels = labels_dense.shape[0]
    index_offset = np.arange(num_labels) * num_classes
    labels_one_hot = np.zeros((num_labels, num_classes))
    labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
    return labels_one_hot


def next_batch(batch_size):
    global train_images
    global train_labels
    global index_in_epoch
    global epochs_completed

    start = index_in_epoch
    index_in_epoch += batch_size

    if index_in_epoch > num_examples:
        epochs_completed += 1
        perm = np.arange(num_examples)
        np.random.shuffle(perm)
        train_images = train_images[perm]
        train_labels = train_labels[perm]
        start = 0
        index_in_epoch = batch_size
        assert batch_size <= num_examples
    end = index_in_epoch
    return train_images[start:end], train_labels[start:end]


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')


data = pd.read_csv('train.csv')
images = data.iloc[:, 1:].values
images = images.astype(np.float32)
images = np.multiply(images, 1.0 / 255.0)
image_size = images.shape[1]
image_width = image_height = np.ceil(np.sqrt(image_size)).astype(np.uint8)

labels_flat = data[[0]].values.ravel()
labels_count = np.unique(labels_flat).shape[0]
labels = dense_to_one_hot(labels_flat, labels_count)
labels = labels.astype(np.uint8)

validation_images = images[:VALIDATION_SIZE]
validation_labels = labels[:VALIDATION_SIZE]

train_images = images[VALIDATION_SIZE:]
train_labels = labels[VALIDATION_SIZE:]

test_images = pd.read_csv('test.csv')
test_images = test_images.astype(np.float32)
test_images = np.multiply(test_images, 1.0 / 255.0)


x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.matmul(x, W) + b
y_ = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
predicted_labels = np.zeros(test_images.shape[0])


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)

# h_drop1 = tf.nn.dropout(h_pool1, keep_prob)

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)
# h_drop2 = tf.nn.dropout(h_pool2, keep_prob)

W_conv3 = weight_variable([5, 5, 64, 128])
b_conv3 = bias_variable([128])

h_conv3 = tf.nn.relu(conv2d(h_pool2, W_conv3) + b_conv3)
# h_drop3 = tf.nn.dropout(h_conv3, keep_prob)

W_fc1 = weight_variable([7 * 7 * 128, 1024])
b_fc1 = bias_variable([1024])

h_pool3_flat = tf.reshape(h_conv3, [-1, 7*7*128])
h_fc1 = tf.nn.relu(tf.matmul(h_pool3_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.matmul(h_fc1_drop, W_fc2) + b_fc2

# cross_entropy = tf.reduce_mean(
#     tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
# train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
predict = tf.argmax(y_conv, 1)

sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
epochs_completed = 0
index_in_epoch = 0
num_examples = train_images.shape[0]

# start TensorFlow session
# init = tf.initialize_all_variables()
# sess = tf.InteractiveSession()

# for _ in range(1000):
#     batch_xs, batch_ys = next_batch(100)
#     sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
#
# # Test trained model
# correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
# accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# print(sess.run(accuracy, feed_dict={x: validation_images,
#                                     y_: validation_labels}))

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_))
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.global_variables_initializer())

for i in range(20000):
  batch = next_batch(BATCH_SIZE)
  if i % 100 == 0:
    train_accuracy = accuracy.eval(feed_dict={
        x: batch[0], y_: batch[1], keep_prob: 1.0})
    print("step %d, training accuracy %g" % (i, train_accuracy))
  train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

print("test accuracy %g" % accuracy.eval(feed_dict={
    x: validation_images, y_: validation_labels, keep_prob: 1.0}))

for i in range(0, test_images.shape[0] // BATCH_SIZE):
    predicted_labels[i * BATCH_SIZE: (i + 1) * BATCH_SIZE] = predict.eval(
        feed_dict={x: test_images[i * BATCH_SIZE: (i + 1) * BATCH_SIZE], keep_prob: 1.0})

np.savetxt('submission1.csv',
           np.c_[range(1, len(test_images) + 1), predicted_labels],
           delimiter=',',
           header='ImageId,Label',
           comments='',
           fmt='%d')

sess.close()