损失函数loss、指标函数metrics

悠悠 2023-07-02 08:27 122阅读 0赞

# ![20191009191333910.png][] #

# [日萌社][Link 1] #

[人工智能AI：Keras PyTorch MXNet TensorFlow PaddlePaddle 深度学习实战（不定时更新）][AI_Keras PyTorch MXNet TensorFlow PaddlePaddle]

--------------------

[tensorflow 2.0 画出model网络模型的拓扑图][tensorflow 2.0 _model]

[tensorflow 2.0 的回调函数callbacks（TensorBoard、ModelCheckpoint）][tensorflow 2.0 _callbacks_TensorBoard_ModelCheckpoint]

[TensorBoard视觉化网络每层权重分布、视觉化网络层结构][TensorBoard]

[MSE(均方误差)、MAE(平均绝对误差)][MSE_MAE]

[from\_logits][from_logits]

[CE(Cross-Entropy)、BCE(Binary Cross-Entropy 即Sigmoid+CE)、CCE(Categorical Cross-Entropy 即Softmax+CE)][CE_Cross-Entropy_BCE_Binary Cross-Entropy _Sigmoid_CE_CCE_Categorical Cross-Entropy _Softmax_CE]

[对连续值/离散值进行预处理的两种方式（标准化/one-hot化）、反标准化/逆标准化、字符串预处理][one-hot]

[损失函数loss、指标函数metrics][loss_metrics]

[激活函数 Sigmoid、Tanh、ReLU、Softmax][Sigmoid_Tanh_ReLU_Softmax]

[Batch Normalization][]

[反向传播、梯度下降、学习率、优化器optimizers（GD、SGD、Momentum、AdaGrad、Adam）][optimizers_GD_SGD_Momentum_AdaGrad_Adam]

[权重初始化对于激活函数的选择：随机常态分布/随机正态分布初始化(标准差为0.01或1)、Xavier(Glorot)初始化、He初始化][0.01_1_Xavier_Glorot_He]

[图像增强(IA)、数据预处理][IA]

[混淆矩阵tf.math.confusion\_matrix][tf.math.confusion_matrix]

[使用预训练网络训练的两种方式：Keras Applications、TensorFlow Hub][Keras Applications_TensorFlow Hub]

--------------------

# **MSE(均方误差)、MAE(平均绝对误差) ** #

1.MSE(均方误差)：
    	np.mean(np.square(真实值y - 预测值y)) / np.mean(真实值y)
    	计算百分比：np.mean(np.square(真实值y - 预测值y)) / np.mean(真实值y) * 100
    
    2.MAE(平均绝对误差)：
    	np.mean(np.abs(真实值y - 预测值y)) / np.mean(真实值y)
    	计算百分比：np.mean(np.abs(真实值y - 预测值y)) / np.mean(真实值y) * 100
    
    3.MSE和MAE都既可作为损失函数loss，也均可作为指标函数。
    	先导入 from tensorflow import keras	
    	损失函数loss：
    		keras.losses.MeanSquaredError()
    		keras.losses.MeanAbsoluteError()
    	指标函数metrics：
    		keras.metrics.MeanSquaredError()
    		keras.metrics.MeanAbsoluteError()
    	
    	例子1：回归模型中的房屋价格预测示例中，在训练期间，比如可以MSE作为损失函数losses，MAE作为指标函数metrics。
    		model.compile(keras.optimizers.Adam(0.001), 
    			     loss=keras.losses.MeanSquaredError(), 
    			     metrics=[keras.metrics.MeanAbsoluteError()])
    	例子2：回归模型中的房屋价格预测示例中，在使用测试数据的预测阶段，同样可以使用MAE作为评价预测结果好坏的标准。
    		np.mean(np.abs(真实价格y - 预测价格y)) / np.mean(真实价格y)

--------------------

# **BCE(Binary Cross-Entropy 实际即Sigmoid激活+CE)** #

# **CCE(Categorical Cross-Entropy 实际即Softmax激活+CE)** #

4.BCE(Binary Cross-Entropy 实际即Sigmoid激活+CE) 既可作为损失函数loss，也均可作为指标函数
    	先导入 from tensorflow import keras	
    	损失函数loss：
    		keras.losses.BinaryCrossentropy()
    	指标函数metrics：
    		keras.metrics.BinaryAccuracy()
    	例子：
    		model.compile(keras.optimizers.Adam(0.001), 
    			     loss=keras.losses.BinaryCrossentropy(), 
    			     metrics=[keras.metrics.BinaryAccuracy()])
     
    5.CCE(Categorical Cross-Entropy 实际即Softmax激活+CE) 既可作为损失函数loss，也均可作为指标函数
    	先导入 from tensorflow import keras	
    	损失函数loss：
    		keras.losses.CategoricalCrossentropy()
    	指标函数metrics：
    		keras.metrics.CategoricalAccuracy()
    	例子：
    		model.compile(keras.optimizers.Adam(0.001), 
    			     loss=keras.losses.CategoricalCrossentropy(), 
    			     metrics=[keras.metrics.CategoricalAccuracy()])

--------------------

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 1][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 2][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 3][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 4][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 5][]

[20191009191333910.png]: https://img-blog.csdnimg.cn/20191009191333910.png
[Link 1]: http://www.rimengshe.com/
[AI_Keras PyTorch MXNet TensorFlow PaddlePaddle]: https://blog.csdn.net/zimiao552147572/article/details/88867161
[tensorflow 2.0 _model]: https://azusa.blog.csdn.net/article/details/104092884
[tensorflow 2.0 _callbacks_TensorBoard_ModelCheckpoint]: https://azusa.blog.csdn.net/article/details/104100362
[TensorBoard]: https://azusa.blog.csdn.net/article/details/104132982
[MSE_MAE]: https://azusa.blog.csdn.net/article/details/104094483
[from_logits]: https://azusa.blog.csdn.net/article/details/104095436
[CE_Cross-Entropy_BCE_Binary Cross-Entropy _Sigmoid_CE_CCE_Categorical Cross-Entropy _Softmax_CE]: https://azusa.blog.csdn.net/article/details/104095759
[one-hot]: https://azusa.blog.csdn.net/article/details/104099669
[loss_metrics]: https://azusa.blog.csdn.net/article/details/104099800
[Sigmoid_Tanh_ReLU_Softmax]: https://azusa.blog.csdn.net/article/details/104108314
[Batch Normalization]: https://azusa.blog.csdn.net/article/details/104115714
[optimizers_GD_SGD_Momentum_AdaGrad_Adam]: https://azusa.blog.csdn.net/article/details/104106429
[0.01_1_Xavier_Glorot_He]: https://azusa.blog.csdn.net/article/details/104110857
[IA]: https://azusa.blog.csdn.net/article/details/104114416
[tf.math.confusion_matrix]: https://azusa.blog.csdn.net/article/details/104125078
[Keras Applications_TensorFlow Hub]: https://azusa.blog.csdn.net/article/details/104134536
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/2020013017054240.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20200130170551933.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 2]: https://img-blog.csdnimg.cn/20200130170604375.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 3]: https://img-blog.csdnimg.cn/2020013017060981.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 4]: https://img-blog.csdnimg.cn/20200130170610567.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0_size_16_color_FFFFFF_t_70 5]: https://img-blog.csdnimg.cn/2020013017061551.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9henVzYS5ibG9nLmNzZG4ubmV0,size_16,color_FFFFFF,t_70