weixin_41196817的博客

使用简单的Keras 的序贯模型大的逻辑结构：model = Sequential() -->model.add() -->model.compile()–>model.fit()–>model.evaluate()model = Sequtntial()没啥好说的了model.add():Conv2D()–>MaxPooling2D()–>Dropou...

1、这个是从.npz 到x_train，y_train，至于从jpg到npz以后再总结：(x_tain,y_train),(x_test,y_test) = mnist.loda_data('mnist.npz')if K.image_data_format() == 'channels first': x_train = x_train.reshape([batch_size,1,img_...