案例:將RNN模型應用於手寫數字識別中
說明:RNN用於圖像識別方面效果可能沒有CNN好。
程序
- 導入庫
import numpy as np
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense
from keras.layers.recurrent import SimpleRNN
from keras.optimizers import Adam
- 加載數據
# 數據長度-一行有28個像素
input_size = 28
# 序列長度-一共有28行
time_steps = 28
# 隱藏層cell個數
cell_size = 50
# 載入數據
(x_train,y_train),(x_test,y_test) = mnist.load_data()
# (60000,28,28)
x_train = x_train/255.0
x_test = x_test/255.0
# 換one hot格式
y_train = np_utils.to_categorical(y_train,num_classes=10)
y_test = np_utils.to_categorical(y_test,num_classes=10)#one hot
- 創建模型+訓練
# 創建模型
model = Sequential()
# 循環神經網絡
model.add(SimpleRNN(
units = cell_size, # 輸出
input_shape = (time_steps,input_size), #輸入
))
# 輸出層
model.add(Dense(10,activation='softmax'))
# 定義優化器
adam = Adam(lr=1e-4)
# 定義優化器,loss function,訓練過程中計算準確率
model.compile(optimizer=adam,loss='categorical_crossentropy',metrics=['accuracy'])
# 訓練模型
model.fit(x_train,y_train,batch_size=64,epochs=10)
# 評估模型
loss,accuracy = model.evaluate(x_test,y_test)
print('test loss',loss)
print('test accuracy',accuracy)
參考:
視頻: 覃秉豐老師的“Keras入門”:http://www.ai-xlab.com/course/32
博客參考:https://www.cnblogs.com/XUEYEYU/tag/keras%E5%AD%A6%E4%B9%A0/