AlexNet是2012年ImageNet競賽冠軍獲得者Hinton和他的學生Alex Krizhevsky設計的。也是在那年之後,更多的更深的神經網路被提出,比如優秀的vgg,GoogLeNet。 這對於傳統的機器學習分類算法而言,已經相當的出色。
基本介紹
- 外文名:AlexNet
- 類型:神經網路
- 提出時間:2012
- 提出者:Hinton及其學生
模型簡介
AlexNet特點
使用了Relu激活函式
標準化
Dropout
AlexNet的TensorFlow實現
# -*- coding=UTF-8 -*- import tensorflow as tf # 輸入數據 import input_data mnist = input_data.read_data_sets("/tmp/data/", one_hot=True) # 定義網路超參數 learning_rate = 0.001 training_iters = 200000 batch_size = 64 display_step = 20 # 定義網路參數 n_input = 784 # 輸入的維度 n_classes = 10 # 標籤的維度 dropout = 0.8 # Dropout 的機率 # 占位符輸入 x = tf.placeholder(tf.types.float32, [None, n_input]) y = tf.placeholder(tf.types.float32, [None, n_classes]) keep_prob = tf.placeholder(tf.types.float32) # 卷積操作 def conv2d(name, l_input, w, b): return tf.nn.relu(tf.nn.bias_add( \ tf.nn.conv2d(l_input, w, strides=[1, 1, 1, 1], padding='SAME'),b) \ , name=name) # 最大下採樣操作 def max_pool(name, l_input, k): return tf.nn.max_pool(l_input, ksize=[1, k, k, 1], \ strides=[1, k, k, 1], padding='SAME', name=name) # 歸一化操作 def norm(name, l_input, lsize=4): return tf.nn.lrn(l_input, lsize, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name=name) # 定義整個網路 def alex_net(_X, _weights, _biases, _dropout): _X = tf.reshape(_X, shape=[-1, 28, 28, 1]) # 向量轉為矩陣 # 卷積層 conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1']) # 下採樣層 pool1 = max_pool('pool1', conv1, k=2) # 歸一化層 norm1 = norm('norm1', pool1, lsize=4) # Dropout norm1 = tf.nn.dropout(norm1, _dropout) # 卷積 conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2']) # 下採樣 pool2 = max_pool('pool2', conv2, k=2) # 歸一化 norm2 = norm('norm2', pool2, lsize=4) # Dropout norm2 = tf.nn.dropout(norm2, _dropout) # 卷積 conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3']) # 下採樣 pool3 = max_pool('pool3', conv3, k=2) # 歸一化 norm3 = norm('norm3', pool3, lsize=4) # Dropout norm3 = tf.nn.dropout(norm3, _dropout) # 全連線層,先把特徵圖轉為向量 dense1 = tf.reshape(norm3, [-1, _weights['wd1'].get_shape().as_list()[0]]) dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1') # 全連線層 dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc2') # Relu activation # 網路輸出層 out = tf.matmul(dense2, _weights['out']) + _biases['out'] return out # 存儲所有的網路參數 weights = { 'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64])), 'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128])), 'wc3': tf.Variable(tf.random_normal([3, 3, 128, 256])), 'wd1': tf.Variable(tf.random_normal([4*4*256, 1024])), 'wd2': tf.Variable(tf.random_normal([1024, 1024])), 'out': tf.Variable(tf.random_normal([1024, 10])) } biases = { 'bc1': tf.Variable(tf.random_normal([64])), 'bc2': tf.Variable(tf.random_normal([128])), 'bc3': tf.Variable(tf.random_normal([256])), 'bd1': tf.Variable(tf.random_normal([1024])), 'bd2': tf.Variable(tf.random_normal([1024])), 'out': tf.Variable(tf.random_normal([n_classes])) } # 構建模型 pred = alex_net(x, weights, biases, keep_prob) # 定義損失函式和學習步驟 cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y)) optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) # 測試網路 correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1)) accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) # 初始化所有的共享變數 init = tf.initialize_all_variables() # 開啟一個訓練 with tf.Session() as sess: sess.run(init) step = 1 # Keep training until reach max iterations while step * batch_size < training_iters: batch_xs, batch_ys = mnist.train.next_batch(batch_size) # 獲取批數據 sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout}) if step % display_step == 0: # 計算精度 acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.}) # 計算損失值 loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.}) print "Iter " + str(step*batch_size) + ", Minibatch Loss= " + "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc) step += 1 print "Optimization Finished!" # 計算測試精度 print "Testing Accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.}) 以上代碼忽略了部分卷積層,全連線層使用了特定的權重。