import tensorflow as tf
x=[1,2]
state=[0.0,0.0]
w_cell_state=np.array([[0.1,0.2],[0.3,0.4]])
w_cell_input=np.array([0.5,0.6])
b_cell=np.array([0.1,-0.1])
w_output=np.array([1.0,2.0])
b_output=0.1
for i in range(len(x)):before_a=np.dot(state,w_cell_state)+x[i]*w_cell_input+b_cell    #初始状态state默认为[0,0]state=np.tanh(before_a)     #当前层的状态statefinal_out=np.dot(state,w_output)+b_output     #得到输出层结果print(before_a)print('state:', state)print('final_out:', final_out)

#定义一个LSTM结构，通过一个简单的命令实现一个完整的LSTM结构
lstm=tf.contrib.rnn.BasicRNNCell(lstm_hidden_size)
#将LSTM中的状态初始化为全0数组，在优化循环神经网络时，每次也会使用一个batch的训练样本。
state=lstm.zero_state(batch_size,tf.float32)
loss=0.0
for i in range(num_steps):#在第一个时刻声明LSTM结构中使用的变量，在之后的时刻都需要复用之前定义好的变量if i>0:tf.get_variable_scope().reuse_variables()#每一步处理时间序列中的一个时刻，将当前输入(current_input)和前一时刻状态(state)传入定义的LSTM结构可以得到当前LSTM结构的输出lstm_output和更新后的状态statelstm_output,state=lstm(current_input,state)#将当前时刻LSTM结构的输出传入一个全连接层得到最后的输出final_output=fully_connected(lstm_output)#计算当前时刻输出的损失loss+=calc_loss(final_output,expected_output)

import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_data
mnist=input_data.read_data_sets('MNIST_data',one_hot=True)
lr=0.001
training_iters=100000
batch_size=128
n_inputs=28     #mnist data input (img shape:28*28)
n_steps=28
n_hidden_units=128   #neurons in hidden layer
n_classes=10     #mnist classes

x=tf.placeholder(tf.float32,[None,n_steps,n_inputs])
y=tf.placeholder(tf.float32,[None,n_classes])
weight={
'in':tf.Variable(tf.random_normal([n_inputs,n_hidden_units])) ,
'out':tf.Variable(tf.random_normal([n_hidden_units,n_classes]))
}
biases={
'in':tf.Variable(tf.constant(0,1,shape=[n_hidden_units,])),
'out':tf.Variable(tf.constant(0.1,shape=[n_classes,]))
}
def RNN(X,weight,biases):X=tf.reshape(X,[-1,n_inputs])X_in=tf.matmul(X,weight['in'])+biases['in']     #shape=[n_steps,n_hidden_units]   biases_shape=[n_hidden_units]X_in=tf.reshape(X_in,[-1,n_steps,n_hidden_units])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)outputs,final_state=tf.nn.dynamic_rnn(lstm_cell,X_in,initial_state=init_state,time_major=False)results=tf.matmul(final_state[1],weight['out'])+biases['out']return results
pred=RNN(x,weight,biases)
cost=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred,labels=y))
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.global_variables_initializer()
with tf.Session() as sess:sess.run(init)step=0while 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