tensorflow勉強会

tensorflow勉強会用の資料

tensorflow勉強会④ MNIST(難しい方)

mint_deep.pyを動かす

もとのコードはこちら
https://raw.githubusercontent.com/tensorflow/tensorflow/master/tensorflow/examples/tutorials/mnist/mnist_deep.py

やはりよくわからないので、やはりこの上なくバカっぽく書き直していきます。

新しく出てくる概念
①畳み込み
②プーリング
 このページがわかりやすいかも!!!動くし。
deepage.net

ドロップアウト
 密結合層のノードを、ある確率で(普通は50%)使わないようにして学習していきます。
 理屈はもろもろありますが、結果的に過学習しづらくなります。

この上なくバカっぽく書き直したコード

import tensorflow as tf
import numpy as np

# 0.よく使う記述は関数に
def conv2d(x, W): # 畳み込み
"""conv2d returns a 2d convolution layer with full stride."""
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')


def max_pool_2x2(x): # プーリング
"""max_pool_2x2 downsamples a feature map by 2X."""
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')


def weight_variable(shape):
"""weight_variable generates a weight variable of a given shape."""
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)


def bias_variable(shape):
"""bias_variable generates a bias variable of a given shape."""
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)


# 1.モデルを作成
x = tf.placeholder(tf.float32, [None, 784])

# Reshape to use within a convolutional neural net.
# Last dimension is for "features" - there is only one here, since images are
# grayscale -- it would be 3 for an RGB image, 4 for RGBA, etc.
x_image = tf.reshape(x, [-1, 28, 28, 1])

# First convolutional layer - maps one grayscale image to 32 feature maps.
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)

# Pooling layer - downsamples by 2X.
h_pool1 = max_pool_2x2(h_conv1)

# Second convolutional layer -- maps 32 feature maps to 64.
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)

# Second pooling layer.
h_pool2 = max_pool_2x2(h_conv2)

# Fully connected layer 1 -- after 2 round of downsampling, our 28x28 image
# is down to 7x7x64 feature maps -- maps this to 1024 features.
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)

# Dropout - controls the complexity of the model, prevents co-adaptation of
# features. ドロップアウト
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# Map the 1024 features to 10 classes, one for each digit
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

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

# 2.学習方法を指定
cross_entropy = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv) )
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))

# 3.コンパイル
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()

# 4.データをロード
train_data = np.loadtxt('train-images.txt')
train_label_pre = np.loadtxt('train-labels.txt')
train_label = np.zeros([60000, 10], dtype=np.float32)
for i in range(60000):
  train_label[i, int(train_label_pre[i])] = 1

test_data = np.loadtxt('test-images.txt')
test_label_pre = np.loadtxt('test-labels.txt')
test_label = np.zeros([10000, 10], dtype=np.float32)
for i in range(10000):
  test_label[i, int(test_label_pre[i])] = 1

# 5.学習 & 6.学習結果のテスト
for iter in range(100):
  print("iter : " + str(iter))
  for i in range( int(60000/100) ):
    batch_xs = train_data[i*100:(i+1)*100, ]
    batch_ys = train_label[i*100:(i+1)*100, ]
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys, keep_prob:0.5})
    print("test accuracy : " + str(sess.run(accuracy, feed_dict={x: test_data, y_: test_label, keep_prob:1.0})))