本周，我們完成整體的環(huán)境搭建：python3.6， Tensorflow1.7.0。
學(xué)習(xí)，實踐各自負(fù)責(zé)的算法部分，如RNN算法，我使用google提供的手寫體識別的MINST數(shù)據(jù)， 來進行熟悉tensorflow框架，以及l(fā)stm算法的具體操作，如下是我的Demo部分代碼：
# -*- coding: utf-8 -*-
import tensorflowas tf
from tensorflow.examples.tutorials.mnistimport input_data
tf.set_random_seed(1)# set random seed
# 導(dǎo)入數(shù)據(jù)
mnist = input_data.read_data_sets('MNIST_data',one_hot=True)
# hyperparameters
lr =0.001? ? ? ? ? ? ? ? ? # learning rate
training_iters =100000? ? # train step 上限
batch_size =128
n_inputs =28? ? ? ? ? ? ? # MNIST data input (img shape: 28*28)
n_steps =28? ? ? ? ? ? ? ? # time steps
n_hidden_units =1024? ? ? # neurons in hidden layer
n_classes =10? ? ? ? ? ? ? # MNIST classes (0-9 digits# )
# x y placeholder
x = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None, n_classes])
# 對 weights biases 初始值的定義
weights = {
# shape (28, 128)
? ? 'in': tf.Variable(tf.random_normal([n_inputs, n_hidden_units])),
# shape (128, 10)
? ? 'out': tf.Variable(tf.random_normal([n_hidden_units, n_classes]))
}
biases = {
# shape (128, )
? ? 'in': tf.Variable(tf.constant(0.1,shape=[n_hidden_units, ])),
# shape (10, )
? ? 'out': tf.Variable(tf.constant(0.1,shape=[n_classes, ]))
}
def RNN(X, weights, biases):
# 原始的 X 是 3 維數(shù)據(jù), 我們需要把它變成 2 維數(shù)據(jù)才能使用 weights 的矩陣乘法
# X ==> (128 batches * 28 steps, 28 inputs)
? ? X = tf.reshape(X, [-1, n_inputs])
# X_in = W*X + b
? ? X_in = tf.matmul(X, weights['in']) + biases['in']
# X_in ==> (128 batches, 28 steps, 128 hidden) 換回3維
? ? X_in = tf.reshape(X_in, [-1, n_steps, n_hidden_units])
# 使用 basic LSTM Cell.
? ? lstm_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden_units,forget_bias=1.0,state_is_tuple=True)
init_state = lstm_cell.zero_state(batch_size,dtype=tf.float32)# 初始化全零 state
? ? outputs, final_state = tf.nn.dynamic_rnn(lstm_cell, X_in,initial_state=init_state,time_major=False)
results = tf.matmul(final_state[1], weights['out']) + biases['out']
return results
pred = RNN(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y,logits=pred))
train_op = tf.train.AdamOptimizer(lr).minimize(cost)
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# init= tf.initialize_all_variables() # tf 馬上就要廢棄這種寫法
# 替換成下面的寫法:
init = tf.global_variables_initializer()
with tf.Session()as sess:
sess.run(init)
step =0
?while step * batch_size < training_iters:
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
batch_xs = batch_xs.reshape([batch_size, n_steps, n_inputs])
sess.run([train_op],feed_dict={
x: batch_xs,
y: batch_ys,
})
if step %20 ==0:
print(sess.run(accuracy,feed_dict={
x: batch_xs,
y: batch_ys,
}))
step +=1
整個Demo數(shù)據(jù)量不大，僅用來熟悉tensorflow的框架，總體來說長短時記憶神經(jīng)網(wǎng)絡(luò)(更善于自然語言處理)對圖形識別不如CNN的效果，但是還是可以達到98%的正確率。
