一個簡單的神經網路(TensorFlow)
阿新 • • 發佈:2019-02-16
1.利用TensorFlow實現一個簡單的例子;
2.重點的知識有:定義權重和輸入輸出的placeholder;前向傳播;反向傳播;優化;損失函式;batch_size的基本概念
3.總結起來,訓練過程可分為三個步驟:
1.定義神經網路的結構和前向傳播;
2.定義損失函式,選擇優化演算法
3.生成會話,選擇batch_size迭代;
import tensorflow as tf from numpy.random import RandomState #通過numpy生成模擬資料集 #定義batch的大小 batch_size = 8 #定義神經網路的引數; w1 = tf.Variable(tf.random_normal([2, 3], stddev=1, seed=1)) w2 = tf.Variable(tf.random_normal([3, 1], stddev=1, seed=1)) x = tf.placeholder(tf.float32, shape=(None, 2), name="x-input") y_ = tf.placeholder(tf.float32, shape=(None, 1), name="y-input") #定義前向傳播; a = tf.matmul(x, w1) y = tf.matmul(a, w2) #定義損失函式(交叉熵)和反向傳播的演算法; y = tf.sigmoid(y) cross_entropy = -tf.reduce_mean( y_ * tf.log(tf.clip_by_value(y, 1e-10, 1.0)) + (1-y_)*tf.log(tf.clip_by_value(1-y, 1e-10, 1.0))) train_step = tf.train.AdamOptimizer(0.001).minimize(cross_entropy) #生成一個模擬資料集; rdm = RandomState(1) dataset_size = 128 X = rdm.rand(dataset_size, 2) Y = [[int(x1+x2 < 1)] for (x1, x2) in X] #建立一個會話執行程式; with tf.Session() as sess: sess.run(tf.global_variables_initializer()) print(sess.run(w1)) print(sess.run(w2)) #設定迭代次數; steps = 5000 for i in range(steps): start = (i * batch_size) % dataset_size end = min(start+batch_size, dataset_size) sess.run(train_step, feed_dict={x: X[start:end], y_: Y[start:end]}) if i % 1000 == 0: total_cross_entropy = sess.run( cross_entropy, feed_dict={x:X, y_:Y}) print(i, total_cross_entropy) print(sess.run(w1)) print(sess.run(w2))
輸出結果如下:
[[-0.8113182 1.4845988 0.06532937]
[-2.4427042 0.0992484 0.5912243 ]]
[[-0.8113182 ]
[ 1.4845988 ]
[ 0.06532937]]
0 0.77943563
1000 0.7338941
2000 0.73070776
3000 0.73061645
4000 0.7305646
[[-0.427144 0.251661 1.6811208]
[-1.8636073 -0.7442908 1.7735264]]
[[ 0.1367231]
[ 0.5396503]
[-1.3507011]]