用RNN做MNIST分类

迈不过友情╰ 2022-06-13 11:49 151阅读 0赞

## 1.前言 ##

RNN常用作NLP中，像图片生成文字、自动生成古诗词等。这篇文章用RNN做MNIST手写数字识别，分类效果虽然没有CNN效果好，但准确率也能够达到96%。

## 2.环境 ##

Mac os系统，python：3.5，Keras

## 3.代码实现 ##

import numpy as np
    np.random.seed(1337)  
    
    from keras.datasets import mnist
    from keras.utils import np_utils
    from keras.models import Sequential
    from keras.layers import SimpleRNN, Activation, Dense
    from keras.optimizers import Adam
    
    TIME_STEPS = 28     
    INPUT_SIZE = 28    
    BATCH_SIZE = 50
    BATCH_INDEX = 0
    OUTPUT_SIZE = 10
    CELL_SIZE = 50
    LR = 0.001
    
    (X_train, y_train), (X_test, y_test) = mnist.load_data()
    
    # data pre-processing
    X_train = X_train.reshape(-1, 28, 28) / 255.      # normalize
    X_test = X_test.reshape(-1, 28, 28) / 255.        # normalize
    y_train = np_utils.to_categorical(y_train, num_classes=10)
    y_test = np_utils.to_categorical(y_test, num_classes=10)
    
    # build RNN model
    model = Sequential()
    
    # RNN cell
    model.add(SimpleRNN(
        batch_input_shape=(None, TIME_STEPS, INPUT_SIZE),       
        output_dim=CELL_SIZE,
        unroll=True,
    ))
    
    # output layer
    model.add(Dense(OUTPUT_SIZE))
    model.add(Activation('softmax'))
    
    # optimizer
    adam = Adam(LR)
    model.compile(optimizer=adam,
                  loss='categorical_crossentropy',
                  metrics=['accuracy'])
    
    # training
    for step in range(40001):
        X_batch = X_train[BATCH_INDEX: BATCH_INDEX+BATCH_SIZE, :, :]
        Y_batch = y_train[BATCH_INDEX: BATCH_INDEX+BATCH_SIZE, :]
        cost = model.train_on_batch(X_batch, Y_batch)
        BATCH_INDEX += BATCH_SIZE
        BATCH_INDEX = 0 if BATCH_INDEX >= X_train.shape[0] else BATCH_INDEX
    
        if step % 500 == 0:
            cost, accuracy = model.evaluate(X_test, y_test, batch_size=y_test.shape[0], verbose=False)
            print('test cost: ', cost, 'test accuracy: ', accuracy)

## 4.结果 ##

![Center][]

[Center]: /images/20220613/dbf9ec81fb144807947ac5bf211e3714.png