問題描述:建立好model之後,用model.fit()函數進行訓練,發現超出顯存容量(一共有12G)
問題分析:fit()函數訓練時,將全部訓練集載入顯存之後,纔開始分批訓練。顯然很容易就超出了12G
解決辦法:用fit_generator函數進行訓練
fit_generator函數將訓練集分批載入顯存,但需要自定義其第一個參數——generator函數,從而分批將訓練集送入顯存
def data_generator(data, targets, batch_size):
batches = (len(data) + batch_size - 1)//batch_size
while(True):
for i in range(batches):
X = data[i*batch_size : (i+1)*batch_size]
Y = targets[i*batch_size : (i+1)*batch_size]
yield (X, Y)
調用fit_generator時的方法
model.fit_generator(generator = data_generator(X_train, Y_train, batch_size),
steps_per_epoch = (len(data) + batch_size - 1) // batch_size,
epochs = num_epochs,
verbose = 1,
callbacks = callbacks,
validation_data = (X_val, Y_val)
)
參考鏈接:https://zhuanlan.zhihu.com/p/23250782
http://blog.csdn.net/sinat_26917383/article/details/74922230