Python 为什么我的模型同时具有较低的MAE和较低的R2分数？

我试图建立一个CNN回归模型。输入数据为10年的卫星图像

输入形状为

[10，256256，10]

，表示

[Year，Image shape，Image shape，Channels/Bands]

模型的输出是一个介于0-1之间的数字，它是图像中区域的百分比值

这些是使用的参数

CHANNELS=5
BATCH_SIZE=16
INPUT_SHAPE=(10,IMG_SIZE,IMG_SIZE,CHANNELS)
SAMPLES=100
LR=1e-7
EPOCHES=10

我使用Conv3D层作为输入层，因为它提供了向模型提供体积数据的能力，而稠密层作为输出

Model: sequential_FLATTEN_100_5_16_SGD_1e-07_30_v1
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv3d_3 (Conv3D)            (None, 10, 254, 254, 32)  1472      
_________________________________________________________________
max_pooling3d_3 (MaxPooling3 (None, 10, 127, 127, 32)  0         
_________________________________________________________________
conv3d_4 (Conv3D)            (None, 10, 125, 125, 64)  18496     
_________________________________________________________________
max_pooling3d_4 (MaxPooling3 (None, 10, 62, 62, 64)    0         
_________________________________________________________________
flatten_3 (Flatten)          (None, 2460160)           0         
_________________________________________________________________
dense_24 (Dense)             (None, 256)               629801216 
_________________________________________________________________
dense_25 (Dense)             (None, 1)                 257       
=================================================================
Total params: 629,821,441
Trainable params: 629,821,441
Non-trainable params: 0
_________________________________________________________________

此模型在训练集上给出以下分数：

mean_absolute_error: 0.09013315520024737
mean_squared_error: 0.11449361186977994
explained_variance_score: -0.2407465861253424
r2_score: -0.9382254392540899

mean_absolute_error: 0.08475626941395917
mean_squared_error: 0.1637630610914996
explained_variance_score: 0.19943303382780664
r2_score: 0.19214565669613703

在验证集上：

mean_absolute_error: 0.1923245317002776
mean_squared_error: 0.2579017795812263
explained_variance_score: -5.067052299015521
r2_score: -5.4177061135705475

mean_absolute_error: 0.15135902269457854
mean_squared_error: 0.2650686092962602
explained_variance_score: -1.7471740284409094
r2_score: -1.7776585146674124

我还尝试了以下不同的模式： 在这种情况下，只有第一层是Conv3D，其余是密集层

Model: "sequential_FLATTEN_100_5_16_Adam_1e-07_30_v1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv3d_1 (Conv3D)            (None, 4, 250, 250, 32)   54912     
_________________________________________________________________
max_pooling3d_1 (MaxPooling3 (None, 1, 83, 83, 32)     0         
_________________________________________________________________
flatten_2 (Flatten)          (None, 220448)            0         
_________________________________________________________________
dense_16 (Dense)             (None, 512)               112869888 
_________________________________________________________________
dense_17 (Dense)             (None, 256)               131328    
_________________________________________________________________
dense_18 (Dense)             (None, 128)               32896     
_________________________________________________________________
dense_19 (Dense)             (None, 64)                8256      
_________________________________________________________________
dense_20 (Dense)             (None, 32)                2080      
_________________________________________________________________
dense_21 (Dense)             (None, 16)                528       
_________________________________________________________________
dense_22 (Dense)             (None, 8)                 136       
_________________________________________________________________
dense_23 (Dense)             (None, 1)                 9         
=================================================================
Total params: 113,100,033
Trainable params: 113,100,033
Non-trainable params: 0
_________________________________________________________________

这给了我以下的训练成绩：

mean_absolute_error: 0.09013315520024737
mean_squared_error: 0.11449361186977994
explained_variance_score: -0.2407465861253424
r2_score: -0.9382254392540899

mean_absolute_error: 0.08475626941395917
mean_squared_error: 0.1637630610914996
explained_variance_score: 0.19943303382780664
r2_score: 0.19214565669613703

在验证集上：

mean_absolute_error: 0.1923245317002776
mean_squared_error: 0.2579017795812263
explained_variance_score: -5.067052299015521
r2_score: -5.4177061135705475

mean_absolute_error: 0.15135902269457854
mean_squared_error: 0.2650686092962602
explained_variance_score: -1.7471740284409094
r2_score: -1.7776585146674124

正如您所见，模型的MAE和MSE非常低，但R2分数和解释方差分数同时也很低

如何改进这些结果？。

---

此外，当样本量增加时，模型开始预测所有输入的相似值。

我注意到，对于这样的任务，参数的数量是如此巨大。可能正在遭受痛苦。尽量减少特征提取程序的尺寸。您也可以在应用退出和正则化之间进行选择。

您可以在此处查看：

---

如果红线表示模型的预测线，那么我认为您的代码缺少一些优化来更全面地概括预测，本质上它至少应该是一条曲线。参考以下url，这是CNN回归的教程：

在上面的教程中，输出图是广义的，这减少了误差。也许你可以试试女士的舞步