Kaysonchen的博客

深度学习笔记（一） 1. 图像归一化 需要归一化至 [0,1] 之间，所以用浮点数 x_train = x_train.reshape(x_train.shape[0], -1).astype('float32')/255 或 x_train = x_train.reshape(x_train.shape[0], -1)/255.0

深度学习笔记（二） 用keras搭建CNN实现MNIST手写数据分类 import numpy as np import pandas as pd import keras from keras.models import Sequential from keras.layers import Dense,Dropout from keras.optimizers import SGD,Adam import matplotlib.pyplot as plt from keras.datasets imp