K折交叉验证:将可用数据划分为K个分区(K通常取4或5),实例化K个相同的模型,将每个模型在K-1个分区上训练,并在剩下的一个分区上进行评估。模型的验证分数等于K个验证分数的平均值。
下面是3折交叉验证的图示:
Keras K折验证部分代码:
import numpy as np
k=4
num_val_samples = len(train_data)//k
num_epochs = 100
all_scores = []
for i in range(k):
print('processing fold #',i)
# 准备第k个分区的数据(验证数据)
val_data = train_data[i*num_val_samples:(i+1)*num_val_samples]
partial_train_data = np.concatenate([train_data[:i*num_val_samples],
train_data[(i+1)*num_val_samples:]],axis=0)
partial_train_targets = np.concatenate([train_targets[:i*num_val_samples],
train_targets[(i+1)*num_val_samples:]],axis=0)
model = build_model()
model.fit(partial_train_data,partial_train_targets,epoch=num_epochs,batch_size=1,verbose=0)
val_mse,val_mae = model.evaluate(val_data,val_targets,verbose=0)
all_scores.append(val_mae)
《python深度学习》第69页