有無GPU執行深度學習mnist資料集時間對比
阿新 • • 發佈:2018-12-18
#硬體配置
*本人用的是 lenovo小新銳7000筆記本,cpu是intel -core -i5-7300Q 四核,記憶體4G,機械硬碟320G,雙顯示卡,整合intel® HD Graphics630 獨顯 GeForce GTX 1050,這塊顯示卡位寬128bit, 視訊記憶體2G,有640個cuda核心。 ##系統環境: win7下,安裝Anaconda3, 之後安裝Python3.6 , Cuda9.0,cudnn9.0 tensorflow1.14.0, Pycharm專業版 ,訓練該資料集用了兩層的卷積神經網路,訓練2萬步,在不開啟GPU加速的情況下用時59分06秒;切換到GPU虛擬環境下用時5分12秒。看來沒有GPU,實踐深度學習確實有難度呀。 附程式碼如下: *
//import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data 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') if __name__ == '__main__': # 讀入資料 mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) # x為訓練影象的佔位符、y_為訓練影象標籤的佔位符 x = tf.placeholder(tf.float32, [None, 784]) y_ = tf.placeholder(tf.float32, [None, 10]) # 將單張圖片從784維向量重新還原為28x28的矩陣圖片 x_image = tf.reshape(x, [-1, 28, 28, 1]) # 第一層卷積層 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) h_pool1 = max_pool_2x2(h_conv1) # 第二層卷積層 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) h_pool2 = max_pool_2x2(h_conv2) # 全連線層,輸出為1024維的向量 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) # 使用Dropout,keep_prob是一個佔位符,訓練時為0.5,測試時為1 keep_prob = tf.placeholder(tf.float32) h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) # 把1024維的向量轉換成10維,對應10個類別 W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2 # 我們不採用先Softmax再計算交叉熵的方法,而是直接用tf.nn.softmax_cross_entropy_with_logits直接計算 cross_entropy = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv)) # 同樣定義train_step train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) # 定義測試的準確率 correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) # 建立Session和變數初始化 sess = tf.InteractiveSession() sess.run(tf.global_variables_initializer()) # 訓練20000步 for i in range(20000): batch = mnist.train.next_batch(50) # 每100步報告一次在驗證集上的準確度 if i % 100 == 0: train_accuracy = accuracy.eval(feed_dict={ x: batch[0], y_: batch[1], keep_prob: 1.0}) print("step %d, training accuracy %g" % (i, train_accuracy)) train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5}) # 訓練結束後報告在測試集上的準確度 print("test accuracy %g" % accuracy.eval(feed_dict={ x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))