shenchenbing
shenchenbing
'pip install pydot' is needed. And don't forget to set environment variable for graphviz. Try again if it works. I met this problem too when I was reading ch7. I...
The original data contains 6 sets of data per hour. So sampling_rate=6 means 1 set of data per hour. The book description is correct.
> callbacks = [ keras.callbacks.ModelCheckpoint( filepath="convnet_from_scratch.keras", save_best_only=True, monitor="val_loss") ] history = model.fit( train_dataset, epochs=30, validation_data=validation_dataset, callbacks=callbacks)这步模型训练报错,input arguments看不出来问题 具体是报了什么错? 我倒是没碰到报错的情况,就是自己跑出来的测试精度和书里面有一些差异。