TensorFlow数据归一化
1. tf.nn.l2_normalize
- l2_normalize(x, dim, epsilon=1e-12,name=None)
- output = x / sqrt(max(sum(x**2), epsilon))
2.使用scikit-learn进行归一化(**numpyarray**)
```
min_max_scaler = preprocessing.MinMaxScaler()
standar_scaler = preprocessing.StandardScaler()
feature_1_scaled = standar_scaler.fit_transform(feature_1)
feature_3_scaled = min_max_scaler.fit_transform(feature_1)
```
3. tensor与numpyarray相互转换
- tf.convert_to_tensor(img.eval())
- print(type(tf.Session().run(tf.constant([1,2,3])))) --*<class 'numpy.ndarray'>*
1
2
3
4
5
6
7
8
9
10
11
12
13
People typically use scikit-learn (StandardScaler) for standardizing data before they train their models on TensorFlow.
def normalize(train, test):
mean, std = train.mean(), test.std()
train = (train - mean) / std
test = (test - mean) / std
return train, test
---------------------
作者：zoray
来源：CSDN
原文：https://blog.csdn.net/zoray/article/details/74276570
版权声明：本文为博主原创文章，转载请附上博文链接！
