Tensorflow 微调VGG-16在Keras中的慢速训练

我试图用LFW数据集对VGG模型的最后两层进行微调，我改变了softmax层的维度，删除了原来的一层，在我的例子中添加了19个输出的softmax层，因为我正在尝试训练19个类。 我还想微调最后一个完全连接的层，以便制作一个“自定义特征提取器”

我正在设置我希望不可培训的层，如下所示：

for layer in model.layers:
    layer.trainable = False

使用gpu，我每一个历元需要1个小时的时间来训练19节课，每节课至少40张图片

因为我没有很多样本，所以这次训练表现有点奇怪

有人知道为什么会这样吗

以下是日志：

Image shape:  (224, 224, 3)
Number of classes:  19
K.image_dim_ordering: th

____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
input_1 (InputLayer)             (None, 3, 224, 224)   0                                            
____________________________________________________________________________________________________
conv1_1 (Convolution2D)          (None, 64, 224, 224)  1792        input_1[0][0]                    
____________________________________________________________________________________________________
conv1_2 (Convolution2D)          (None, 64, 224, 224)  36928       conv1_1[0][0]                    
____________________________________________________________________________________________________
pool1 (MaxPooling2D)             (None, 64, 112, 112)  0           conv1_2[0][0]                    
____________________________________________________________________________________________________
conv2_1 (Convolution2D)          (None, 128, 112, 112) 73856       pool1[0][0]                      
____________________________________________________________________________________________________
conv2_2 (Convolution2D)          (None, 128, 112, 112) 147584      conv2_1[0][0]                    
____________________________________________________________________________________________________
pool2 (MaxPooling2D)             (None, 128, 56, 56)   0           conv2_2[0][0]                    
____________________________________________________________________________________________________
conv3_1 (Convolution2D)          (None, 256, 56, 56)   295168      pool2[0][0]                      
____________________________________________________________________________________________________
conv3_2 (Convolution2D)          (None, 256, 56, 56)   590080      conv3_1[0][0]                    
____________________________________________________________________________________________________
conv3_3 (Convolution2D)          (None, 256, 56, 56)   590080      conv3_2[0][0]                    
____________________________________________________________________________________________________
pool3 (MaxPooling2D)             (None, 256, 28, 28)   0           conv3_3[0][0]                    
____________________________________________________________________________________________________
conv4_1 (Convolution2D)          (None, 512, 28, 28)   1180160     pool3[0][0]                      
____________________________________________________________________________________________________
conv4_2 (Convolution2D)          (None, 512, 28, 28)   2359808     conv4_1[0][0]                    
____________________________________________________________________________________________________
conv4_3 (Convolution2D)          (None, 512, 28, 28)   2359808     conv4_2[0][0]                    
____________________________________________________________________________________________________
pool4 (MaxPooling2D)             (None, 512, 14, 14)   0           conv4_3[0][0]                    
____________________________________________________________________________________________________
conv5_1 (Convolution2D)          (None, 512, 14, 14)   2359808     pool4[0][0]                      
____________________________________________________________________________________________________
conv5_2 (Convolution2D)          (None, 512, 14, 14)   2359808     conv5_1[0][0]                    
____________________________________________________________________________________________________
conv5_3 (Convolution2D)          (None, 512, 14, 14)   2359808     conv5_2[0][0]                    
____________________________________________________________________________________________________
pool5 (MaxPooling2D)             (None, 512, 7, 7)     0           conv5_3[0][0]                    
____________________________________________________________________________________________________
flatten (Flatten)                (None, 25088)         0           pool5[0][0]                      
____________________________________________________________________________________________________
fc6 (Dense)                      (None, 4096)          102764544   flatten[0][0]                    
____________________________________________________________________________________________________
fc7 (Dense)                      (None, 4096)          16781312    fc6[0][0]                        
____________________________________________________________________________________________________
batchnormalization_1 (BatchNorma (None, 4096)          16384       fc7[0][0]                        
____________________________________________________________________________________________________
fc8 (Dense)                      (None, 19)            77843       batchnormalization_1[0][0]       
====================================================================================================
Total params: 134,354,771
Trainable params: 16,867,347
Non-trainable params: 117,487,424
____________________________________________________________________________________________________
None
Train on 1120 samples, validate on 747 samples
Epoch 1/20
1120/1120 [==============================] - 7354s - loss: 2.9517 - acc: 0.0714 - val_loss: 2.9323 - val_acc: 0.2316
Epoch 2/20
1120/1120 [==============================] - 7356s - loss: 2.8053 - acc: 0.1732 - val_loss: 2.9187 - val_acc: 0.3614
Epoch 3/20
1120/1120 [==============================] - 7358s - loss: 2.6727 - acc: 0.2643 - val_loss: 2.9034 - val_acc: 0.3882
Epoch 4/20
1120/1120 [==============================] - 7361s - loss: 2.5565 - acc: 0.3071 - val_loss: 2.8861 - val_acc: 0.4016
Epoch 5/20
1120/1120 [==============================] - 7360s - loss: 2.4597 - acc: 0.3518 - val_loss: 2.8667 - val_acc: 0.4043
Epoch 6/20
1120/1120 [==============================] - 7363s - loss: 2.3827 - acc: 0.3714 - val_loss: 2.8448 - val_acc: 0.4163
Epoch 7/20
1120/1120 [==============================] - 7364s - loss: 2.3108 - acc: 0.4045 - val_loss: 2.8196 - val_acc: 0.4244
Epoch 8/20
1120/1120 [==============================] - 7377s - loss: 2.2463 - acc: 0.4268 - val_loss: 2.7905 - val_acc: 0.4324
Epoch 9/20
1120/1120 [==============================] - 7373s - loss: 2.1824 - acc: 0.4563 - val_loss: 2.7572 - val_acc: 0.4404
Epoch 10/20
1120/1120 [==============================] - 7373s - loss: 2.1313 - acc: 0.4732 - val_loss: 2.7190 - val_acc: 0.4471
Epoch 11/20
1120/1120 [==============================] - 7440s - loss: 2.0766 - acc: 0.5036 - val_loss: 2.6754 - val_acc: 0.4565
Epoch 12/20
1120/1120 [==============================] - 7414s - loss: 2.0323 - acc: 0.5170 - val_loss: 2.6263 - val_acc: 0.4565
Epoch 13/20
1120/1120 [==============================] - 7413s - loss: 1.9840 - acc: 0.5420 - val_loss: 2.5719 - val_acc: 0.4592
Epoch 14/20
1120/1120 [==============================] - 7414s - loss: 1.9467 - acc: 0.5464 - val_loss: 2.5130 - val_acc: 0.4592
Epoch 15/20
1120/1120 [==============================] - 7412s - loss: 1.9039 - acc: 0.5652 - val_loss: 2.4513 - val_acc: 0.4592
Epoch 16/20
1120/1120 [==============================] - 7413s - loss: 1.8716 - acc: 0.5723 - val_loss: 2.3906 - val_acc: 0.4578
Epoch 17/20
1120/1120 [==============================] - 7415s - loss: 1.8214 - acc: 0.5866 - val_loss: 2.3319 - val_acc: 0.4538
Epoch 18/20
1120/1120 [==============================] - 7416s - loss: 1.7860 - acc: 0.5982 - val_loss: 2.2789 - val_acc: 0.4538
Epoch 19/20
1120/1120 [==============================] - 7430s - loss: 1.7623 - acc: 0.5973 - val_loss: 2.2322 - val_acc: 0.4538
Epoch 20/20
1120/1120 [==============================] - 7856s - loss: 1.7222 - acc: 0.6170 - val_loss: 2.1913 - val_acc: 0.4538
Accuracy: 45.38%

---

结果不太好，因为我无法训练它获取更多数据，因为它需要太长时间。有什么想法吗？

请注意，为了训练

16867347

参数，您需要输入

~19*40<800

示例。因此，这基本上是每个示例的

2e6

参数。这根本无法正常工作。尝试删除所有

FCN

层（

density

层位于顶部），并放置较小的

density

，每个层大约有50个神经元。在我看来，这应该有助于提高准确性和加快训练

在《玛辛·莫伊科的沉迷》中——接下来呢：1。移除顶部（致密）层。2.计算图像的网络输出（这样就有19*40个向量）。3.在这个向量上训练你的新密集部分。4.结合这两个网络（CNN和Dense）（无论如何，请注意，可能不会给出太好的结果）。我想了想，你想的是从图像中提取特征，然后用这些特征训练连续的稠密层？是的。只需从图像中提取特征向量并训练密集层。也许你会得到一个可以接受的结果。好吧，我明天会试试，我会告诉你仍然很慢，但它有效。我在80%的准确率和1.9的损失与20个时代的验证，所以也许我需要更多的数据为每个类…是的，我知道，我尝试过，但性能很差，如验证精度冻结在20%，每类至少有20个图像。因此，我计划更改我的数据集，因为LFW有很多类只有一个图像，所以如果我使用每个类具有更多表示的faceScrub，它将更好地与原始VGG一起工作，显然，使用100个类，每个类至少有200个图像，即……你认为如何？谢谢！！你觉得计算时间怎么样？我改变了数据集（现在我使用的是faceScrub），我尝试了你提出的方法，每个有2个密度的128个神经元，但仍然很慢。我认为这来自于卷积层，因为我的图像尺寸是224*224。我现在的结果是

val_loss:2.4294-val_acc:0.8350

对50个类别进行分类，每个类别23张图像，我应该采集更多数据吗？丢失功能减少得非常慢您的批处理大小是多少？我安装了tensorflow的两个版本（gpu和cpu），默认keras采用cpu版本，所以我删除了这个版本，它工作了。。。。谢谢！！！：）