我正在尝试建立一个网络来检测脸部的68个界标（x，y）。训练和验证图像的320x320x3规格为-0.5至0.5。我的标签是136个logit，每个在0到1.0之间，对应于X->（0，320）； Y->（0，320）。损失函数是keras“ root_mean_square”。训练数据集中的图像数量约为5k。在训练过程中，我的训练和验证损失从大约6.0开始，并在100次迭代中减少到大约0.0022，但随后似乎在该水平达到饱和，并且没有任何降低。我已经尝试了2000次迭代。从输出看，似乎网络学会了在帧中心以脸部形状输出68个点，而与实际位置无关。
我正在使用生成器来获取数据，并使用sklearn.utils.shuffle()来确保我的数据被正确地重新整理。
一些帖子建议网络可能过拟合，因为它对于一个简单的问题是如此复杂，因此我尝试了一个约10层的非常简单的网络和约20层的复杂网络，但我的结果仍然相同。我的当前网络如下所示，我使用了2个跳过连接，3个辍学和l2正则化器来确保我的网络不会过拟合。拟合不足应该不是问题，因为我已经尝试对网络进行多达2000次迭代的训练。
对于如何解决此问题的任何建议，我们将不胜感激。谢谢！
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) (None, 320, 320, 3) 0
__________________________________________________________________________________________________
conv2d_1 (Conv2D) (None, 320, 320, 3) 228 input_1[0][0]
__________________________________________________________________________________________________
batch_normalization_1 (BatchNor (None, 320, 320, 3) 12 conv2d_1[0][0]
__________________________________________________________________________________________________
activation_1 (Activation) (None, 320, 320, 3) 0 batch_normalization_1[0][0]
__________________________________________________________________________________________________
max_pooling2d_1 (MaxPooling2D) (None, 160, 160, 3) 0 activation_1[0][0]
__________________________________________________________________________________________________
conv2d_2 (Conv2D) (None, 160, 160, 8) 608 max_pooling2d_1[0][0]
__________________________________________________________________________________________________
batch_normalization_2 (BatchNor (None, 160, 160, 8) 32 conv2d_2[0][0]
__________________________________________________________________________________________________
activation_2 (Activation) (None, 160, 160, 8) 0 batch_normalization_2[0][0]
__________________________________________________________________________________________________
max_pooling2d_2 (MaxPooling2D) (None, 80, 80, 8) 0 activation_2[0][0]
__________________________________________________________________________________________________
conv2d_3 (Conv2D) (None, 80, 80, 16) 1168 max_pooling2d_2[0][0]
__________________________________________________________________________________________________
conv2d_4 (Conv2D) (None, 80, 80, 16) 2320 conv2d_3[0][0]
__________________________________________________________________________________________________
batch_normalization_3 (BatchNor (None, 80, 80, 16) 64 conv2d_4[0][0]
__________________________________________________________________________________________________
activation_3 (Activation) (None, 80, 80, 16) 0 batch_normalization_3[0][0]
__________________________________________________________________________________________________
max_pooling2d_4 (MaxPooling2D) (None, 40, 40, 16) 0 activation_3[0][0]
__________________________________________________________________________________________________
conv2d_5 (Conv2D) (None, 40, 40, 32) 4640 max_pooling2d_4[0][0]
__________________________________________________________________________________________________
conv2d_6 (Conv2D) (None, 40, 40, 32) 9248 conv2d_5[0][0]
__________________________________________________________________________________________________
conv2d_7 (Conv2D) (None, 40, 40, 32) 9248 conv2d_6[0][0]
__________________________________________________________________________________________________
batch_normalization_4 (BatchNor (None, 40, 40, 32) 128 conv2d_7[0][0]
__________________________________________________________________________________________________
activation_4 (Activation) (None, 40, 40, 32) 0 batch_normalization_4[0][0]
__________________________________________________________________________________________________
max_pooling2d_6 (MaxPooling2D) (None, 20, 20, 32) 0 activation_4[0][0]
__________________________________________________________________________________________________
dropout_1 (Dropout) (None, 20, 20, 32) 0 max_pooling2d_6[0][0]
__________________________________________________________________________________________________
conv2d_8 (Conv2D) (None, 20, 20, 64) 18496 dropout_1[0][0]
__________________________________________________________________________________________________
conv2d_9 (Conv2D) (None, 20, 20, 64) 36928 conv2d_8[0][0]
__________________________________________________________________________________________________
max_pooling2d_3 (MaxPooling2D) (None, 20, 20, 16) 0 conv2d_4[0][0]
__________________________________________________________________________________________________
conv2d_10 (Conv2D) (None, 20, 20, 64) 36928 conv2d_9[0][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 20, 20, 80) 0 max_pooling2d_3[0][0]
conv2d_10[0][0]
__________________________________________________________________________________________________
batch_normalization_5 (BatchNor (None, 20, 20, 80) 320 concatenate_1[0][0]
__________________________________________________________________________________________________
activation_5 (Activation) (None, 20, 20, 80) 0 batch_normalization_5[0][0]
__________________________________________________________________________________________________
max_pooling2d_7 (MaxPooling2D) (None, 10, 10, 80) 0 activation_5[0][0]
__________________________________________________________________________________________________
dropout_2 (Dropout) (None, 10, 10, 80) 0 max_pooling2d_7[0][0]
__________________________________________________________________________________________________
conv2d_11 (Conv2D) (None, 10, 10, 128) 92288 dropout_2[0][0]
__________________________________________________________________________________________________
conv2d_12 (Conv2D) (None, 10, 10, 128) 147584 conv2d_11[0][0]
__________________________________________________________________________________________________
max_pooling2d_5 (MaxPooling2D) (None, 10, 10, 32) 0 conv2d_7[0][0]
__________________________________________________________________________________________________
conv2d_13 (Conv2D) (None, 10, 10, 128) 147584 conv2d_12[0][0]
__________________________________________________________________________________________________
concatenate_2 (Concatenate) (None, 10, 10, 160) 0 max_pooling2d_5[0][0]
conv2d_13[0][0]
__________________________________________________________________________________________________
batch_normalization_6 (BatchNor (None, 10, 10, 160) 640 concatenate_2[0][0]
__________________________________________________________________________________________________
activation_6 (Activation) (None, 10, 10, 160) 0 batch_normalization_6[0][0]
__________________________________________________________________________________________________
max_pooling2d_8 (MaxPooling2D) (None, 5, 5, 160) 0 activation_6[0][0]
__________________________________________________________________________________________________
dropout_3 (Dropout) (None, 5, 5, 160) 0 max_pooling2d_8[0][0]
__________________________________________________________________________________________________
flatten_2 (Flatten) (None, 4000) 0 dropout_3[0][0]
__________________________________________________________________________________________________
dense_3 (Dense) (None, 1024) 4097024 flatten_2[0][0]
__________________________________________________________________________________________________
dense_4 (Dense) (None, 136) 139400 dense_3[0][0]
==================================================================================================
Total params: 4,744,888
Trainable params: 4,744,290
Non-trainable params: 598
__________________________________________________________________________________________________