from tensorflow.examples.tutorials.mnist import input_datamnist=input_data.read_data_sets("../MNIST_data",one_hot=True)import tensorflow as tfimport numpy as npfrom tensorflow.python.ops.control_flow_ops import constant_op#参数设置learning_rate=0.001training_iters=100000batch_size=128display_step=10#Network Parmetersn_input=28 # MNIST data input (img shape: 28*28)n_steps=28 # timestepsn_hidden=128 #hidden layer num of featuresn_class=10 #MNIST total class(0-9 digits)#tf graph inputx=tf.placeholder(tf.float32,[None,n_steps,n_input])# Tensorflow LSTM cell requires 2x n_hidden length (state & cell)istate_fw=tf.placeholder(tf.float32,[None,2*n_hidden])istate_bw=tf.placeholder(tf.float32,[None,2*n_hidden])y=tf.placeholder(tf.float32,[None,n_class])#define weightsweights={ 'hidden':tf.Variable(tf.random_normal([n_input,2*n_hidden])), 'out':tf.Variable(tf.random_normal([2*n_hidden,n_class]))}biases={ 'hidden':tf.Variable(tf.random_normal([2*n_hidden,])), 'out':tf.Variable(tf.random_normal([n_class,]))}def BiRNN(_X,_isstate_fw,_istate_bw,_weights,_biases,_batch_size,_seq_len): _seq_len=tf.fill([_batch_size],constant_op.constant(_seq_len,dtype=tf.int64)) # _X=tf.transpose(_X,[1,0,2]) # _X=tf.reshape(_X,[-1,n_input]) # _X=tf.matmul(_X,_weights['hidden'])+_biases['hidden'] # # # Define lstm cells with tensorflow # lstm_fw_cell=tf.nn.rnn_cell.BasicLSTMCell(n_hidden,forget_bias=1.0) # # Backward direction cell # lstm_bw_cell=tf.nn.rnn_cell.BasicLSTMCell(n_hidden,forget_bias=1.0) # # Split data because rnn cell needs a list of inputs for the RNN inner loop # _X=tf.split(_X,n_steps,0) # # Get lstm cell output # outputs=tf.nn.static_bidirectional_rnn(lstm_fw_cell,lstm_bw_cell,_X, # initial_state_fw=_isstate_fw, # initial_state_bw=_iinputs must be a sequencestate_bw, # sequence_length=_seq_lesequence_length=_seq_lenn) # Define lstm cells with tensorflow lstm_fw_cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden,forget_bias=1.0) # Backward direction cell lstm_bw_cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden,forget_bias=1.0) outputs,output_states= tf.nn.bidirectional_dynamic_rnn(lstm_fw_cell, lstm_bw_cell, _X,dtype=tf.float32) outputs=tf.concat(outputs, 2) outputs = tf.transpose(outputs, [1, 0, 2]) return tf.matmul(outputs[-1],_weights['out'])+ _biases['out']pred=BiRNN(x,istate_fw,istate_bw,weights,biases,batch_size,n_steps)cost=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred,labels=y))optimizer=tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)# Evaluate modelcorrect_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()with tf.Session() as sess: sess.run(init) step=1 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_input) sess.run(optimizer,feed_dict={ x:batch_xs,y:batch_ys, istate_fw:np.zeros((batch_size,2*n_hidden)), istate_bw:np.zeros((batch_size,2*n_hidden)) }) if step % display_step == 0: # Calculate batch accuracy acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, istate_fw: np.zeros((batch_size, 2 * n_hidden)), istate_bw: np.zeros((batch_size, 2 * n_hidden))}) # Calculate batch loss loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, istate_fw: np.zeros((batch_size, 2 * n_hidden)), istate_bw: np.zeros((batch_size, 2 * n_hidden))}) print( "Iter " + str(step * batch_size) + ", Minibatch Loss= " + "{:.6f}".format(loss) + \ ", Training Accuracy= " + "{:.5f}".format(acc)) step += 1 print( "Optimization Finished!") # Calculate accuracy for 128 mnist test images test_len = 128 test_data = mnist.test.images[:test_len].reshape((-1, n_steps, n_input)) test_label = mnist.test.labels[:test_len] print("Testing Accuracy:", sess.run(accuracy, feed_dict={x: test_data, y: test_label, istate_fw: np.zeros((test_len, 2 * n_hidden)), istate_bw: np.zeros((test_len, 2 * n_hidden))}))
扫一扫
2万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
