update

MorvanZhou · Morvan Zhou · commit 504f4b452fc3 · 2017-05-11T13:07:45.000+10:00
diff --git a/tutorial-contents/401_CNN.py b/tutorial-contents/401_CNN.py
@@ -18,7 +18,7 @@
 BATCH_SIZE = 50
 LR = 0.001              # learning rate
 
-mnist = input_data.read_data_sets('./mnist', one_hot=True)
+mnist = input_data.read_data_sets('./mnist', one_hot=True)  # they has been normalized to range (0,1)
 test_x = mnist.test.images[:2000]
 test_y = mnist.test.labels[:2000]
 
@@ -29,7 +29,7 @@
 plt.title('%i' % np.argmax(mnist.train.labels[0]))
 plt.show()
 
-tf_x = tf.placeholder(tf.float32, [None, 28*28])/255.  # normalize to range (0, 1)
+tf_x = tf.placeholder(tf.float32, [None, 28*28])
 image = tf.reshape(tf_x, [-1, 28, 28, 1])              # (batch, height, width, channel)
 tf_y = tf.placeholder(tf.int32, [None, 10])            # input y
 
diff --git a/tutorial-contents/402_RNN_classification.py b/tutorial-contents/402_RNN_classification.py
@@ -22,7 +22,7 @@
 LR = 0.01               # learning rate
 
 # data
-mnist = input_data.read_data_sets('./mnist', one_hot=True)
+mnist = input_data.read_data_sets('./mnist', one_hot=True)              # they has been normalized to range (0,1)
 test_x = mnist.test.images[:2000]
 test_y = mnist.test.labels[:2000]
 
@@ -34,7 +34,7 @@
 plt.show()
 
 # tensorflow placeholders
-tf_x = tf.placeholder(tf.float32, [None, TIME_STEP * INPUT_SIZE])/255.  # shape(batch, 784), normalize to range (0, 1)
+tf_x = tf.placeholder(tf.float32, [None, TIME_STEP * INPUT_SIZE])       # shape(batch, 784)
 image = tf.reshape(tf_x, [-1, TIME_STEP, INPUT_SIZE])                   # (batch, height, width, channel)
 tf_y = tf.placeholder(tf.int32, [None, 10])                             # input y
 
diff --git a/tutorial-contents/403_RNN_regression.py b/tutorial-contents/403_RNN_regression.py
@@ -48,8 +48,7 @@
 train_op = tf.train.AdamOptimizer(LR).minimize(loss)
 
 sess = tf.Session()
-init_op = tf.group(tf.global_variables_initializer())
-sess.run(init_op)     # initialize var in graph
+sess.run(tf.global_variables_initializer())     # initialize var in graph
 
 plt.figure(1, figsize=(12, 5))
 plt.ion()           # continuously plot
diff --git a/tutorial-contents/404_AutoEncoder.py b/tutorial-contents/404_AutoEncoder.py
@@ -0,0 +1,101 @@
+"""
+Know more, visit my Python tutorial page: https://morvanzhou.github.io/tutorials/
+My Youtube Channel: https://www.youtube.com/user/MorvanZhou
+
+Dependencies:
+tensorflow: 1.1.0
+matplotlib
+numpy
+"""
+import tensorflow as tf
+from tensorflow.examples.tutorials.mnist import input_data
+import matplotlib.pyplot as plt
+from mpl_toolkits.mplot3d import Axes3D
+from matplotlib import cm
+import numpy as np
+
+tf.set_random_seed(1)
+
+# Hyper Parameters
+BATCH_SIZE = 64
+LR = 0.002         # learning rate
+N_TEST_IMG = 5
+
+# Mnist digits
+mnist = input_data.read_data_sets('./mnist', one_hot=False)     # use not one-hotted target data
+test_x = mnist.test.images[:200]
+test_y = mnist.test.labels[:200]
+
+# plot one example
+print(mnist.train.images.shape)     # (55000, 28 * 28)
+print(mnist.train.labels.shape)     # (55000, 10)
+plt.imshow(mnist.train.images[0].reshape((28, 28)), cmap='gray')
+plt.title('%i' % np.argmax(mnist.train.labels[0]))
+plt.show()
+
+# tf placeholder
+tf_x = tf.placeholder(tf.float32, [None, 28*28])    # value in the range of (0, 1)
+
+# encoder
+en0 = tf.layers.dense(tf_x, 128, tf.nn.tanh)
+en1 = tf.layers.dense(en0, 64, tf.nn.tanh)
+en2 = tf.layers.dense(en1, 12, tf.nn.tanh)
+encoded = tf.layers.dense(en2, 3)
+
+# decoder
+de0 = tf.layers.dense(encoded, 12, tf.nn.tanh)
+de1 = tf.layers.dense(de0, 64, tf.nn.tanh)
+de2 = tf.layers.dense(de1, 128, tf.nn.tanh)
+decoded = tf.layers.dense(de2, 28*28, tf.nn.sigmoid)
+
+loss = tf.losses.mean_squared_error(labels=tf_x, predictions=decoded)
+train = tf.train.AdamOptimizer(LR).minimize(loss)
+
+sess = tf.Session()
+sess.run(tf.global_variables_initializer())
+
+# initialize figure
+f, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2))
+plt.ion()   # continuously plot
+plt.show()
+
+# original data (first row) for viewing
+view_data = mnist.test.images[:N_TEST_IMG]
+for i in range(N_TEST_IMG):
+    a[0][i].imshow(np.reshape(view_data[i], (28, 28)), cmap='gray')
+    a[0][i].set_xticks(())
+    a[0][i].set_yticks(())
+
+for step in range(8000):
+    b_x, b_y = mnist.train.next_batch(BATCH_SIZE)
+    _, encoded_, decoded_, loss_ = sess.run([train, encoded, decoded, loss], {tf_x: b_x})
+
+    if step % 100 == 0:     # plotting
+        print('train loss: %.4f' % loss_)
+        # plotting decoded image (second row)
+        decoded_data = sess.run(decoded, {tf_x: view_data})
+        for i in range(N_TEST_IMG):
+            a[1][i].clear()
+            a[1][i].imshow(np.reshape(decoded_data[i], (28, 28)), cmap='gray')
+            a[1][i].set_xticks(())
+            a[1][i].set_yticks(())
+        plt.draw()
+        plt.pause(0.01)
+
+plt.ioff()
+
+# visualize in 3D plot
+view_data = test_x[:200]
+encoded_data = sess.run(encoded, {tf_x: view_data})
+fig = plt.figure(2)
+ax = Axes3D(fig)
+X = encoded_data[:, 0]
+Y = encoded_data[:, 1]
+Z = encoded_data[:, 2]
+for x, y, z, s in zip(X, Y, Z, test_y):
+    c = cm.rainbow(int(255*s/9))
+    ax.text(x, y, z, s, backgroundcolor=c)
+ax.set_xlim(X.min(), X.max())
+ax.set_ylim(Y.min(), Y.max())
+ax.set_zlim(Z.min(), Z.max())
+plt.show()
