1.手写数字数据集
- from sklearn.datasets import load_digits
- digits = load_digits()
2.图片数据预处理
- x：归一化MinMaxScaler()
- y：独热编码OneHotEncoder()或to_categorical
- 训练集测试集划分
- 张量结构
-
X_train, X_test, y_train, y_test = train_test_split(XL, Y, test_size=0.2, random_state=0, stratify=Y)
print('X_train.shape, X_test.shape, y_train.shape, y_test.shape：', X_train.shape, X_test.shape, y_train.shape, y_test.shape)
3.设计卷积神经网络结构
- 绘制模型结构图，并说明设计依据。
4.模型训练
5.模型评价
- model.evaluate()
- 交叉表与交叉矩阵
- pandas.crosstab
- seaborn.heatmap
