2020-9-29循环神经网络.py

'''
多层循环神经网络：

tf.nn.rnn_cell.DropoutWrapper( cell,
    input_keep_prob=1.0,
    output_keep_prob=1.0,
    state_keep_prob=1.0,
    variational_recurrent=False,
    input_size=None,
    dtype=None,
    seed=None,
    dropout_state_filter_visitor=None)

cell：层的类型。一般是RNNCell类型，主要的输入有定义好的tf.nn.rnn_cell.BasicRNNCell或者tf.nn.rnn_cell.LSTMCell
input_keep_prob：一个概率，int类型。希望输入有多少神经元被保留
output_keep_prob：一个概率，int类型。希望输出有多少神经元被保留

tf.nn.rnn_cell.DeviceCellWrapper,这个包装器只是代理每个方法调用到另一个单元格

'''
import numpy as np
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()

# layers = [tf.nn.rnn_cell.BasicCell()]

(X_train, y_train), (X_test, y_test) = tf.keras.datasets.mnist.load_data()
X_train = X_train.astype(np.float32).reshape(-1, 28*28) / 255.0
X_test = X_test.astype(np.float32).reshape(-1, 28*28) / 255.0
y_train = y_train.astype(np.int32)
y_test = y_test.astype(np.int32)
X_valid, X_train = X_train[:5000], X_train[5000:]
y_valid, y_train = y_train[:5000], y_train[5000:]

def shuffle_batch(X, y, batch_size):
    rnd_idx = np.random.permutation(len(X))
    n_batches = len(X) // batch_size
    for batch_idx in np.array_split(rnd_idx, n_batches):
        X_batch, y_batch = X[batch_idx], y[batch_idx]
        yield X_batch, y_batch
n_steps = 28
n_inputs = 28
n_neurons = 150
n_outputs = 10
n_layers = 3

learning_rate = 0.001

X = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.int32, [None])

lstm_cells = [tf.nn.rnn_cell.BasicLSTMCell(num_units=n_neurons)
              for layer in range(n_layers)]
multi_cell = tf.nn.rnn_cell.MultiRNNCell(lstm_cells)
outputs, states = tf.nn.dynamic_rnn(multi_cell, X, dtype=tf.float32)
top_layer_h_state = states[-1][1]
logits = tf.layers.dense(top_layer_h_state, n_outputs, name="softmax")
xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=logits)
loss = tf.reduce_mean(xentropy, name="loss")
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
training_op = optimizer.minimize(loss)
correct = tf.nn.in_top_k(logits, y, 1)
accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))
init = tf.global_variables_initializer()
n_epochs = 10
batch_size = 150

with tf.Session() as sess:
    init.run()
    for epoch in range(n_epochs):
        for X_batch, y_batch in shuffle_batch(X_train, y_train, batch_size):
            X_batch = X_batch.reshape((-1, n_steps, n_inputs))
            sess.run(training_op, feed_dict={X: X_batch, y: y_batch})
        acc_batch = accuracy.eval(feed_dict={X: X_batch, y: y_batch})
        acc_test = accuracy.eval(feed_dict={X: X_test, y: y_test})
        print(epoch, "Last batch accuracy:", acc_batch, "Test accuracy:", acc_test)