1. 训练结果保存
hist=model.fit(train_set_x,train_set_y,batch_size=256)
# 或 hist=model.fit_generator(gen,batch_size=256)
with open('log_sgd_big_32.txt','w') as f:
f.write(str(hist.history))
2. 利用Tensorboard可视化训练
参考:https://blog.csdn.net/dugudaibo/article/details/77961836
from keras.callbacks import TensorBoard
model.fit(train_data, train_labels,
nb_epoch=400, batch_size=32,
callbacks=[TensorBoard(log_dir='mytensorboard/3')]) # log_dir是tensorboard文件保存地址
之后打开终端,进入conda——>activate到装有tensorflow的环境中。
conda
source activate env
之后在终端中输入
tensorboard --logdir='/home/lib321/my_keras/mytensorboard/3'