質問編集履歴

全体のコードを追加しました

2019/02/12 10:49

投稿

vaitarika

スコア29

test CHANGED Viewed

File without changes

test CHANGED Viewed

@@ -64,6 +64,356 @@
 ```
+下記が全体のコードです
+```python
+import sys
+import os
+import numpy as np
+import tensorflow as tf
+import tensorflow.python.platform
+from tensorflow.examples.tutorials.mnist import input_data
+mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
+NUM_CLASSES = 10
+IMAGE_SIZE = 28
+IMAGE_PIXELS = IMAGE_SIZE*IMAGE_SIZE
+flags = tf.app.flags
+FLAGS = flags.FLAGS
+flags.DEFINE_integer('max_steps', 20, 'Number of steps to run trainer.')
+flags.DEFINE_integer('batch_size', 1024, 'Batch size'
+                     'Must divide evenly into the dataset sizes.')
+flags.DEFINE_float('learning_rate', 1e-4, 'Initial learning rate.')
+def inference(images_placeholder, keep_prob):
+    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_image = tf.reshape(images_placeholder, [-1, IMAGE_SIZE, IMAGE_SIZE, 1])
+    print(x_image.shape)
+    # 畳み込み層1の作成
+    with tf.name_scope('conv1') as scope:
+        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)
+    # プーリング層1の作成
+    with tf.name_scope('pool1') as scope:
+        h_pool1 = max_pool_2x2(h_conv1)
+    # 畳み込み層2の作成
+    with tf.name_scope('conv2') as scope:
+        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)
+    # プーリング層2の作成
+    with tf.name_scope('pool2') as scope:
+        h_pool2 = max_pool_2x2(h_conv2)
+    # 畳み込み層3の作成
+    with tf.name_scope('conv3') as scope:
+        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)
+    # プーリング層3の作成
+    with tf.name_scope('pool3') as scope:
+        h_pool3 = max_pool_2x2(h_conv3)
+    # 全結合層1の作成
+    with tf.name_scope('fc1') as scope:
+        W_fc1 = weight_variable([7*7*128, 1024])
+        b_fc1 = bias_variable([1024])
+        h_pool3_flat = tf.reshape(h_pool3, [-1, 7*7*128])
+        h_fc1 = tf.nn.relu(tf.matmul(h_pool3_flat, W_fc1) + b_fc1)
+        h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
+    # 全結合層2の作成
+    with tf.name_scope('fc2') as scope:
+        W_fc2 = weight_variable([1024, NUM_CLASSES])
+        b_fc2 = bias_variable([NUM_CLASSES])
+    with tf.name_scope('softmax') as scope:
+        y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
+    return y_conv
+def loss(logits, labels):
+    cross_entropy = -tf.reduce_sum(labels*tf.log(logits))
+    tf.summary.scalar("cross_entropy", cross_entropy)
+    return cross_entropy
+def training(loss, learning_rate):
+    train_step = tf.train.AdamOptimizer(learning_rate).minimize(loss)
+    return train_step
+def accuracy(logits, labels):
+    correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(labels, 1))
+    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
+    tf.summary.scalar("accuracy", accuracy)
+    return accuracy
+if __name__ == '__main__':
+    with tf.Graph().as_default():
+        images_placeholder = tf.placeholder("float", shape=(None, IMAGE_PIXELS))
+        labels_placeholder = tf.placeholder("float", shape=(None, NUM_CLASSES))
+        keep_prob = tf.placeholder("float")
+        logits = inference(images_placeholder, keep_prob)
+        loss_value = loss(logits, labels_placeholder)
+        train_op = training(loss_value, FLAGS.learning_rate)
+        acc = accuracy(logits, labels_placeholder)
+        saver = tf.train.Saver()
+        sess = tf.Session()
+        sess.run(tf.global_variables_initializer())
+        summary_op = tf.summary.merge_all()
+        summary_writer = tf.summary.FileWriter('./logs', sess.graph)
+        for step in range(FLAGS.max_steps):
+            for i in range(int(len(mnist.train.images)/FLAGS.batch_size)):
+                batch = FLAGS.batch_size * i
+                sess.run(train_op, feed_dict={
+                  images_placeholder: mnist.train.images[batch:batch+FLAGS.batch_size],
+                  labels_placeholder: mnist.train.labels[batch:batch+FLAGS.batch_size],
+                  keep_prob: 0.5})
+            train_accuracy = sess.run(acc, feed_dict={
+                images_placeholder: mnist.train.images,
+                labels_placeholder: mnist.train.labels,
+                keep_prob: 1.0})
+            print ("step {}, training accuracy {}".format(step, train_accuracy))
+            summary_str = sess.run(summary_op, feed_dict={
+                images_placeholder: mnist.train.images,
+                labels_placeholder: mnist.train.labels,
+                keep_prob: 1.0})
+            summary_writer.add_summary(summary_str, step)
+            print ("test accuracy {}".format(sess.run(acc, feed_dict={
+                images_placeholder: mnist.test.images,
+                labels_placeholder: mnist.test.labels,
+                keep_prob: 1.0})))
+            summary_str_1 = sess.run(summary_op, feed_dict={
+                images_placeholder: mnist.test.images,
+                labels_placeholder: mnist.test.labels,
+                keep_prob: 1.0})
+            summary_writer.add_summary(summary_str_1, step)
+    cwd = os.getcwd()
+    save_path = saver.save(sess, cwd + "//model.ckpt")
+    sess = tf.InteractiveSession()
+    saver.restore(sess, "model.ckpt")
+```
 ### 補足情報
 開発環境