我实现了一个神经网络keras,具有以下结构:
model = Sequential([... layers ...])
model.compile(optimizer=..., loss=...)
hist=model.fit(x=X,y=Y, validation_split=0.1, epochs=100)
有没有办法从任一提取model或hist火车和验证集？也就是说,我想知道哪些指标的X和Y被用于训练和被用于验证.
How can I randomly split my image dataset into training and validation datesets? More specifically, the validation_split argument in Keras ImageDataGenerator function is not randomly splitting my images into training and validation but is slicing the validation sample from an unshuffled dataset.