我們將要搭建一個簡單的卷積神經網絡結構去提高手寫數字的預測結果精度。
# Introductory CNN Model: MNIST Digits
# In this example, we will download the MNIST?handwritten
# digits and create a simple CNN network to predict the
# digit category (0-9)
主要分為以下幾個步驟：導入數據；創建模型的變量；搭建模型；采用批量化訓練網絡；可視化loss，accuracy等結果。
1.導入必要的庫和開始一個圖譜會話
import tensorflow as tf
import numpy as np
import matplotlib as plt
from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets
sess = tf.Session()
2.導入數據集和將圖片裝換為28 * 28大小的矩陣
data_dir = 'temp'?? #數據集存放的文件夾
mnist = read_data_sets(data_dir)????? #讀取數據集
#將訓練和測試數據集圖片歸一化為28*28大小
train_xdata = np.array([np.reshape(x, (28,28)) for x in mnist.train.images])
test_xdata = np.array([np.reshape(x, (28,28)) for x in mnist.test.images])
train_labels = mnist.train.labels??? #訓練數據集標簽
test_labels = mnist.test.labels?????? #測試數據集標簽
3.定義模型參數
batch_size = 100?????? #一個批量的圖片數量
learning_rate = 0.005?????????? #學習率
evaluation_size = 500????????? #模型驗證數據集一個批量的數量
image_width = train_xdata[0].shape[0]????? #圖片的長 28
image_height = train_xdata[0].shape[1]???? #圖片的寬 28
target_size = max(train_labels)+1??? #輸出類別的個數 10
num_channels = 1???????????????????????????? # 通道數為1
generations = 500????????????????????????????? #迭代代數
eval_every = 5 ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?#每次5個generation
conv1_features = 25????????????????????????? #卷積核的個數
conv2_features = 50????????????????????????? #卷積核的個數
max_pool_size1 = 2????????????????????????? #池化層窗口大小
max_pool_size2 = 2????????????????????????? #池化層窗口大小
fully_connected_size1 = 100??????????? #全連接層大小
4.定義數據集的占位符
#輸入數據的張量大小
x_input_shape = (batch_size, image_width, image_height, num_channels)
#創建輸入訓練數據的占位符
x_input = tf.placeholder(tf.float32, shape=x_input_shape)? ? ? ? ?
#創建一個批量訓練結果的占位符
y_target = tf.placeholder(tf.int32, shape=batch_size)? ? ? ? ?
#驗證圖片輸入張量
eval_input_shape = (evaluation_size, image_width, image_height,num_channels)
#創建輸入驗證數據的占位符
eval_input = tf.placeholder(tf.float32, shape=eval_input_shape)? ??
#創建一個批量驗證結果的占位符
eval_target = tf.placeholder(tf.int32, shape= evaluation_size )??
5.定義訓練權重和偏置的變量
#定義第一個卷積核的參數，其中用tf.truncated_normal生成正太分布的數據，#stddev（正態分布標準差）為0.1
conv1_weight = tf.Variable(tf.truncated_normal([4, 4, num_channels, conv1_features], stddev=0.1, dtype = tf.float32))
#定義第一個卷積核對應的偏置
conv1_bias = tf.Variable(tf.zeros([conv1_features], dtype=tf.float32))
#定義第二個卷積核的參數，其中用tf.truncated_normal生成正太分布的數據，#stddev（正態分布標準差）為0.1
conv2_weight = tf.Variable(tf.truncated_normal([4, 4, num_channels, conv2_features], stddev=0.1, dtype = tf.float32))
#定義第二個卷積核對應的偏置
conv2_bias = tf.Variable(tf.zeros([conv2_features], dtype=tf.float32))
6.定義全連接層的權重和偏置
#輸出卷積特征圖的大小
resulting_width = image_width // (max_pool_size1 * max_pool_size2)
resulting_height = image_height // (max_pool_size1 * max_pool_size2)
#將卷積層特征圖拉成一維向量
full1_input_size = resulting_width * resulting_height * conv2_features
#創建第一個全連接層權重和偏置
full1_weight =tf.Variable(tf.truncated_normal([full1_input_size,fully_connected_size1],
?????????????????????????????????????????????? stddev=0.1, dtype=tf.float32))
full1_bias = tf.Variable(tf.truncated_normal([fully_connected_size1], stddev=0.1,
?????????????????????????????????????????????? dtype=tf.float32))
#創建第二個全連接層權重和偏置
full2_weight = tf.Variable(tf.truncated_normal([fully_connected_size1,target_size],
?????????????????????????????????????????????? stddev=0.1, dtype=tf.float32))
full2_bias = tf.Variable(tf.truncated_normal([target_size], stddev=0.1,
?????????????????????????????????????????????? dtype=tf.float32))
7.定義網絡模型
def my_conv_net(input_data):
??? #First Conv-relu-maxpool layer
??? conv1 = tf.nn.conv2d(input_data, conv1_weight, strides=[1, 1, 1, 1], padding='SAME')
??? relu1 = tf.nn.relu(tf.nn.bias_add(conv1, conv1_bias))
??? max_pool1 = tf.nn.max_pool(relu1, ksize=[1, max_pool_size1, max_pool_size1, 1],? strides=[1, max_pool_size1, max_pool_size1, 1], padding='SAME')
??? # Second Conv-relu-maxpool layer
??? conv2 = tf.nn.conv2d(max_pool1, conv2_weight, strides=[1, 1, 1, 1], padding='SAME')
??? relu2 = tf.nn.relu(tf.nn.bias_add(conv2, conv2_bias))
??? max_pool2 = tf.nn.max_pool(relu2, ksize=[1, max_pool_size1, max_pool_size1, 1],? strides=[1, max_pool_size2, max_pool_size2, 1], padding='SAME')
??? #將輸出轉換為一個[1xN],為下一個全連接層輸入做準備
??? final_conv_shape = max_pool2.get_shape().as_list()
??? final_shape = final_conv_shape[1] * final_conv_shape[2] * final_conv_shape[3]
??? flat_output = tf.reshape(max_pool2, [final_conv_shape[0], final_shape])
??? #First fully-connected layer
??? fully_connected1 = tf.nn.relu(tf.add(tf.add(tf.matmul(flat_output,full1_weight), full1_bias)))
?? ?# Second fully-connected layer
??? final_model_output = tf.add(tf.matmul(fully_connected1, full2_weight), full2_bias)
??? return (final_model_output)
8.定義網絡的訓練數據和測數據
model_output = my_conv_net(x_input)
test_model_output = my_conv_net(eval_input)
9.使用Softmax函數作為loss function
loss = loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(logits=model_output, labels=y_target))
10.接下來創建一個訓練和測試的函數
prediction = tf.nn.softmax(model_output)
test_prediction = tf.nn.softmax(test_model_output)
# Create accuracy function
def get_accuracy(logits, targets):
? ? batch_predictions = np.argmax(logits, axis=1)
? ? num_correct = np.sum(np.equal(batch_predictions, targets))
return(100. * num_correct/batch_predictions.shape[0])
11.創建一個optimizer function
my_optimizer = tf.train.MomentumOptimizer(learning_rate, 0.9)
train_step = my_optimizer.minimize(loss)
# Initialize Variables
init = tf.initialize_all_variables()
sess.run(init)
12.開始訓練模型
train_loss = [ ]
train_acc = [ ]
test_acc = [ ]
for i in range(generations):
? ? rand_index = np.random.choice(len(train_xdata), size=batch_size)
? ? rand_x = train_xdata[rand_index]
? ? rand_x = np.expand_dims(rand_x, 3)
? ? rand_y = train_labels[rand_index]
? ? train_dict = {x_input: rand_x, y_target: rand_y}
? ? sess.run(train_step, feed_dict=train_dict)
? ? temp_train_loss, temp_train_preds = sess.run([loss,?prediction], feed_dict=train_dict)
? ? temp_train_acc = get_accuracy(temp_train_preds, rand_y)
? ? if (i+1) % eval_every == 0:
? ? ? ? eval_index = np.random.choice(len(test_xdata),?size=evaluation_size)
? ? ? ? eval_x = test_xdata[eval_index]
? ? ? ? eval_x = np.expand_dims(eval_x, 3)
? ? ? ? eval_y = test_labels[eval_index]
? ? ? ? test_dict = {eval_input: eval_x, eval_target: eval_y}
? ? ? ? test_preds = sess.run(test_prediction, feed_dict=test_dict)
? ? ? ? temp_test_acc = get_accuracy(test_preds, eval_y)
? ? ? ? # Record and print results
? ? ? ? train_loss.append(temp_train_loss)
? ? ? ? train_acc.append(temp_train_acc)
? ? ? ? test_acc.append(temp_test_acc)
? ? ? ? acc_and_loss = [(i+1), temp_train_loss, temp_train_acc,?temp_test_acc]
? ? ? ? acc_and_loss = [np.round(x,2) for x in acc_and_loss]
13.輸出結果
print('Generation # {}. Train Loss: {:.2f}. Train Acc (Test Acc):?{:.2f} ({:.2f})'.format(*acc_and_loss))
14.使用matplotlib顯示loss-accuracies曲線
eval_indices = range(0, generations, eval_every)
# Plot loss over time
plt.plot(eval_indices, train_loss, 'k-')
plt.title('Softmax Loss per Generation')
plt.xlabel('Generation')
plt.ylabel('Softmax Loss')
plt.show()
# Plot train and test accuracy
plt.plot(eval_indices, train_acc, 'k-', label='Train Set Accuracy')
plt.plot(eval_indices, test_acc, 'r--', label='Test Set Accuracy')
plt.title('Train and Test Accuracy')
plt.xlabel('Generation')
plt.ylabel('Accuracy')
plt.legend(loc='lower right')
plt.show()
15.顯示最新一個批量的預測結果
# Plot the 6 of the last batch results:
actuals = rand_y[0:6]
predictions = np.argmax(temp_train_preds,axis=1)[0:6]
images = np.squeeze(rand_x[0:6])
Nrows = 2
Ncols = 3
for i in range(6):
? ? plt.subplot(Nrows, Ncols, i+1)
? ? plt.imshow(np.reshape(images[i], [28,28]), cmap='Greys_r')
? ? plt.title('Actual: ' + str(actuals[i]) + ' Pred: ' + str(predi
? ? ctions[i]),fontsize=10)
? ? frame = plt.gca()
? ? frame.axes.get_xaxis().set_visible(False)
? ? frame.axes.get_yaxis().set_visible(False)
