验证准确性不会增加培训ResNet50 [英] validation accuracy is not increasing training ResNet50
问题描述
我正在对ResNet50模型进行微调，以使用数据引证进行人脸识别，但是观察到模型的准确性正在提高，但是从一开始的验证准确性并没有提高，我没有弄错哪里出了问题，请查看我的代码.
I was doing fine-tuning with ResNet50 model for face recognition using data agumentation, but observed that the model accuracy was increasing but validation accuracy from the very starting point is not imporving, i am not getting where is it getting wrong, please review my code.
我尝试操纵添加的顶层，但没有帮助.
I have tried manipulating the top layers which i have added but it didn't helped.
import os
os.environ['KERAS_BACKEND'] = 'tensorflow'
from keras.applications import ResNet50
from keras.models import Sequential
from keras.layers import Dense, Flatten, GlobalAveragePooling2D,Input,Dropout
num_classes = 13
base = ResNet50(include_top=False, weights='resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',input_tensor=Input(shape=(100,100,3)))
from keras.models import Model
x = base.output
#x = GlobalAveragePooling2D()(x)
x = Flatten()(x)
x = Dense(1024, activation = 'relu')(x)
x = Dropout(0.5)(x)
predictions = Dense(13, activation='softmax')(x)
model = Model(inputs=base.input, outputs=predictions)
for layers in base.layers:
layers.trainable= False
model.compile(optimizer='sgd', loss='categorical_crossentropy', metrics=['accuracy'])
from keras.preprocessing.image import ImageDataGenerator
train_generator = ImageDataGenerator(featurewise_center=True,
rotation_range=20,
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
width_shift_range=0.2,
height_shift_range=0.2,
horizontal_flip=True)
test_generator = ImageDataGenerator(rescale=1./255)
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(image,label,test_size=0.2,shuffle=True,random_state=0)
train_generator.fit(x_train)
test_generator.fit(x_test)
model.fit_generator(train_generator.flow(x_train,y_train,batch_size=32),
steps_per_epoch =10,epochs=50,
validation_data=test_generator.flow(x_test,y_test))
输出:
Epoch 19/50
10/10 [==============================] - 105s 10s/step - loss: 1.9387 - acc: 0.3803 - val_loss: 2.6820 - val_acc: 0.0709
Epoch 20/50
10/10 [==============================] - 107s 11s/step - loss: 2.0725 - acc: 0.3230 - val_loss: 2.6689 - val_acc: 0.0709
Epoch 21/50
10/10 [==============================] - 103s 10s/step - loss: 1.8884 - acc: 0.3375 - val_loss: 2.6677 - val_acc: 0.0709
Epoch 22/50
10/10 [==============================] - 95s 10s/step - loss: 1.8265 - acc: 0.4051 - val_loss: 2.6799 - val_acc: 0.0709
Epoch 23/50
10/10 [==============================] - 100s 10s/step - loss: 1.8346 - acc: 0.3812 - val_loss: 2.6929 - val_acc: 0.0709
Epoch 24/50
10/10 [==============================] - 102s 10s/step - loss: 1.9547 - acc: 0.3352 - val_loss: 2.6952 - val_acc: 0.0709
Epoch 25/50
10/10 [==============================] - 104s 10s/step - loss: 1.9472 - acc: 0.3281 - val_loss: 2.7168 - val_acc: 0.0709
Epoch 26/50
10/10 [==============================] - 103s 10s/step - loss: 1.8818 - acc: 0.4063 - val_loss: 2.7071 - val_acc: 0.0709
Epoch 27/50
10/10 [==============================] - 106s 11s/step - loss: 1.8053 - acc: 0.4000 - val_loss: 2.7059 - val_acc: 0.0709
Epoch 28/50
10/10 [==============================] - 104s 10s/step - loss: 1.9601 - acc: 0.3493 - val_loss: 2.7104 - val_acc: 0.0709
推荐答案
之所以发生这种情况，是因为我只是直接添加完全连接的层而没有先对其进行培训，如keras博客中所述， https://blog.keras. io/building-powerful-image-classification-models-using-very-little-data.html
It was happening because i was just directly adding the fully-connected layers without training it first, as mentioned in Blog of keras, https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html
为了执行微调，所有层都应从经过适当训练的权重开始:例如，您不应在预先训练的卷积基础上拍打随机初始化的完全连接的网络.这是因为由随机初始化的权重触发的大梯度更新将破坏卷积基础中的学习权重.在我们的案例中，这就是为什么我们首先训练顶级分类器，然后才开始对它进行微调卷积权重的原因.
in order to perform fine-tuning, all layers should start with properly trained weights: for instance you should not slap a randomly initialized fully-connected network on top of a pre-trained convolutional base. This is because the large gradient updates triggered by the randomly initialized weights would wreck the learned weights in the convolutional base. In our case this is why we first train the top-level classifier, and only then start fine-tuning convolutional weights alongside it.
所以答案是首先分别训练顶级模型，然后创建一个具有ResNet50模型的新模型，其权重，顶级模型及其权重都位于resnet模型(基础模型)的顶部，然后通过冻结对其进行首次训练基本模型(ResNet50)和基础模型的最后一层.
so answer is first train the top-model separately, then create a new model having ResNet50 model with its weight, with top-model and its weights on top of resnet model(base-model), then train it first by freezing the base-model(ResNet50) and the with the last layer of the base-model.
这篇关于验证准确性不会增加培训ResNet50的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
