tensorboard的使用

1、keras 与 tensorboard

from tensorflow.keras.callbacks import TensorBoard
filepath="snapshot/v2_weights-improvement-{epoch:02d}-{val_acc:.2f}.hdf5" tensorboard = TensorBoard(log_dir='logs/{}'.format(filepath)) callbacks_list = [checkpoint, tensorboard] model.fit(train_imgs, train_labels, validation_data=(test_imgs, test_labels) , batch_size=256, callbacks=callbacks_list, epochs=15, shuffle=True, verbose=0)

 终端  tensorboard --logdir="./log"

   http://localhost:6006(如果访问的是服务器,别忘记修改ip)

   https://*.com/questions/42112260/how-do-i-use-the-tensorboard-callback-of-keras

 

上一篇:'Tensorboard.util' has no attribute 'Retrier'


下一篇:2018年终总结