# -*- coding:utf-8 _*-
"""@author:zhangxianke
@file: test.py
@time: 2018/11/09
"""from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
data = input_data.read_data_sets('./mnist_data', one_hot= true)
train_x, train_y = data.train.images, data.train.labels
test_x, test_y = data.test.images, data.test.labels
sequence_length = 28 #整個rnn結構輸入序列數（手寫體字行數）
frame_size = 28 #每個序列中的元素個數(每行資料中的元素個數)
n_hidden = 100 #隱藏層
n_class = 10
w = tf.variable(tf.random_normal([n_hidden, n_class]), dtype= tf.float32)
b = tf.variable(tf.zeros([1,n_class]), dtype= tf.float32)
x = tf.placeholder(tf.float32, [none, sequence_length * frame_size])
y = tf.placeholder(tf.float32, [none, n_class])
def rnn(_x, _w, _b):
_x = tf.reshape(_x, shape= [-1, sequence_length, frame_size])
cell = tf.nn.rnn_cell.basicrnncell(n_hidden) # rnn單元
output, h = tf.nn.dynamic_rnn(cell, _x, dtype= tf.float32)
return tf.nn.softmax(tf.matmul(output[:, -1, :], w) + b)
iters = 1000
batch = 1280
learn_rate = 0.001
y_predict = rnn(x, w, b)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y_predict, labels= y))
optm = tf.train.adamoptimizer(learn_rate).minimize(loss)
result = tf.equal(tf.argmax(y_predict, 1), tf.argmax(y, 1))
acc = tf.reduce_mean(tf.to_float(result))
#init
sess = tf.session()
sess.run(tf.global_variables_initializer())
for i in range(iters):
cost = count = 0.0
for batch_index in range(0, train_y.shape[0], batch):
count += 1
feed =
sess.run(optm, feed_dict= feed)
cost += sess.run(loss, feed_dict=feed)
cost /= count
feed_test =
accuracy = sess.run(acc, feed_dict= feed_test)
print ('第 %d 次迭代, 損失函式值為 %.6f, 準確率為 %.6f' % (i + 1, cost, accuracy))
基於Tensorflow和keras的RNN網路
1.簡單的rnn網路 rnn的公式可以是y wh b 簡單的rnn網路也被稱為elman網路。2.改進的rnn網路 當輸出取決於序列的前乙個和後乙個元素時，使用雙向rnn brnn brnn通過堆疊兩個rnn 前向層和後向層 來實現，並且輸出都是rnn隱藏狀態的結果。在前向層中，記憶狀態h從時間步長...
普通神經網路tensorflow例子1
隨機生成200個樣本，每個樣本2個特徵，輸出2個類別 import tensorflow as tf import matplotlib.pyplot as plt from sklearn.datasets import make classification defset color y if ...
反卷積實現 tensorflow 實現
deconv解卷積，實際是叫做conv transpose,conv transpose實際是卷積的乙個逆向過程，tf中，編寫conv transpose 的時候，心中想著乙個正向的卷積過程會很有幫助。想象一下我們有乙個正向卷積 input shape 1,5,5,3 kernel shape 2,...