Question

在我的项目中，有3个人的面孔，我想对他们的面孔进行分类。因此，在我的训练集中，每个人有500个样本，每个人的验证集有500个样本。使用resnet50预训练模型对人脸进行分类。但是，验证损失和准确性都不好。代码如下：

resnet = ResNet50(input_shape=IMAGE_SIZE + [3], weights='imagenet', include_top=False)

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

x = Flatten()(resnet.output)
prediction = Dense(len(folders), activation='softmax')(x)

model = Model(inputs=resnet.input, outputs=prediction)
model.compile(
  loss='categorical_crossentropy',
  optimizer='adam',
  metrics=['accuracy']
)
from keras.preprocessing.image import ImageDataGenerator

train_datagen = ImageDataGenerator(rescale = 1./255,
                                   shear_range = 0.2,
                                   zoom_range = 0.2,
                                   horizontal_flip = True)

test_datagen = ImageDataGenerator(rescale = 1./255)

training_set = train_datagen.flow_from_directory('drive/My Drive/faces/train',
                                                 target_size = (224, 224),
                                                 batch_size = 16,
                                                 class_mode = 'categorical')

test_set = test_datagen.flow_from_directory('drive/My Drive/faces/val',
                                            target_size = (224, 224),
                                            batch_size = 16,
                                            class_mode = 'categorical')

# fit the model
r = model.fit_generator(
  training_set,
  validation_data=test_set,
  epochs=5,
  steps_per_epoch=len(training_set),
  validation_steps=len(test_set)
)

训练准确性，损失，有效性和损失如下：

[！[https://i.stack.imgur.com/0P2iW.png][1]][1]

为什么验证损失会增加而验证准确性却没有提高？

如何减少验证损失并提高准确性？

0 个答案: