迁移学习准确性差

Mic*_* S. 4 python machine-learning keras tensorflow transfer-learning

我的任务是根据缺陷对种子进行分类。我有 7 个类的大约 14k 图像(它们的大小不相等,有些类有更多照片,有些类有更少)。我尝试从头开始训练 Inception V3,准确率约为 90%。然后我尝试使用带有 ImageNet 权重的预训练模型进行迁移学习。我inception_v3applications没有顶级 fc 层的情况下导入,然后在文档中添加了我自己的层。我以以下代码结束:

# Setting dimensions
img_width = 454
img_height = 227

###########################
# PART 1 - Creating Model #
###########################

# Creating InceptionV3 model without Fully-Connected layers
base_model = InceptionV3(weights='imagenet', include_top=False, input_shape = (img_height, img_width, 3))

# Adding layers which will be fine-tunned
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(1024, activation='relu')(x)
predictions = Dense(7, activation='softmax')(x)

# Creating final model
model = Model(inputs=base_model.input, outputs=predictions)

# Plotting model
plot_model(model, to_file='inceptionV3.png')

# Freezing Convolutional layers
for layer in base_model.layers:
    layer.trainable = False

# Summarizing layers
print(model.summary())

# Compiling the CNN
model.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])

##############################################
# PART 2 - Images Preproccessing and Fitting #
##############################################

# Fitting the CNN to the images

train_datagen = ImageDataGenerator(rescale = 1./255,
                                   rotation_range=30,
                                   width_shift_range=0.2,
                                   height_shift_range=0.2,
                                   shear_range = 0.2,
                                   zoom_range = 0.2,
                                   horizontal_flip = True,
                                   preprocessing_function=preprocess_input,)

valid_datagen = ImageDataGenerator(rescale = 1./255,
                                   preprocessing_function=preprocess_input,)

train_generator = train_datagen.flow_from_directory("dataset/training_set",
                                                    target_size=(img_height, img_width),
                                                    batch_size = 4,
                                                    class_mode = "categorical",
                                                    shuffle = True,
                                                    seed = 42)

valid_generator = valid_datagen.flow_from_directory("dataset/validation_set",
                                                    target_size=(img_height, img_width),
                                                    batch_size = 4,
                                                    class_mode = "categorical",
                                                    shuffle = True,
                                                    seed = 42)

STEP_SIZE_TRAIN = train_generator.n//train_generator.batch_size
STEP_SIZE_VALID = valid_generator.n//valid_generator.batch_size

# Save the model according to the conditions  
checkpoint = ModelCheckpoint("inception_v3_1.h5", monitor='val_acc', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)
early = EarlyStopping(monitor='val_acc', min_delta=0, patience=10, verbose=1, mode='auto')

#Training the model
history = model.fit_generator(generator=train_generator,
                         steps_per_epoch=STEP_SIZE_TRAIN,
                         validation_data=valid_generator,
                         validation_steps=STEP_SIZE_VALID,
                         epochs=25,
                         callbacks = [checkpoint, early])
Run Code Online (Sandbox Code Playgroud)

但我得到了可怕的结果:45% 的准确率。我想应该会更好。我有一些假设可能会出现问题:

  • 我从头开始对缩放图像(299x299)和非缩放图像进行迁移学习(227x454)训练,但它失败了(或者可能我失败了尺寸顺序)。
  • 当我使用迁移学习时preprocessing_function=preprocess_input(在网上发现文章非常重要,所以我决定添加它)。
  • 添加了rotation_range=30width_shift_range=0.2height_shift_range=0.2、 和horizontal_flip = True同时迁移学习以进一步增强数据。
  • 也许 Adam 优化器是个坏主意?例如,我应该尝试 RMSprop 吗?
  • 我是否也应该使用学习率较小的 SGD 来微调一些卷积层?

还是我在其他方面失败了?

编辑:我发布了训练历史的情节。也许它包含有价值的信息:

历史训练情节

EDIT2:随着 InceptionV3 参数的变化:

更改参数的 InceptionV3

VGG16 对比:

VGG16 进行比较

Mic*_* S. 5

@今天,我发现一个问题。这是因为批量归一化层及其冻结时的行为发生了一些变化。Chollet先生给出了一个解决方法,但我使用了datumbox制作的Keras fork,这解决了我的问题。主要问题描述如下:

https://github.com/keras-team/keras/pull/9965

现在我的准确率约为 85%,并正在努力提高它。