数据挖掘 - 微调精度低于原始迁移学习精度 - 吾爱随笔录

我在 Inception V3 上使用迁移学习，在 Keras 上使用 ImageNet 权重，在 python 2.7 上使用 Tensorflow 后端来创建图像分类器。我首先从 Inception 中提取并保存了瓶颈特征，并用它们来训练一个全连接层。这个 FC 给了我大约 86% 的训练准确率。然后，我通过将经过训练的 FC 层粘贴在裸照 Inception V3 的顶部来“微调”模型，并使用 SGD、低学习率和高动量与前两个卷积块一起重新训练。我还在训练图像上使用了图像增强，但仅限于微调阶段。这个模型没有提高准确率，而是几乎没有给我 60% 的准确率，并且比裸迁移学习模型表现更差。

1.为什么会这样？

可选：2.我可以做些什么来提高我在这个模型上“一般”的准确性？我要分类的图像来自 BreakHis 乳腺肿瘤数据库，是一项相当困难的分类任务。迁移学习是否适合这项任务？

具有瓶颈特征的迁移学习代码：

import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dropout, Dense, GlobalAveragePooling2D
from keras.applications.inception_v3 import InceptionV3,preprocess_input
from keras.utils.np_utils import to_categorical
from keras.callbacks import ModelCheckpoint, EarlyStopping
import math

img_width, img_height = (299, 299)
weight_path = 'bottleneck_fc_model.h5'
train_dir = 'Cancer_Data/Train'
validation_dir = 'Cancer_Data/Validate'
epochs = 150
batch_size = 128



def train_top_model():
    datagen_top = ImageDataGenerator(preprocessing_function=preprocess_input)
    generator_top = datagen_top.flow_from_directory(
    train_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='categorical',
    shuffle=False)

nb_classes = len(generator_top.class_indices)
np.save('class_indices.npy', generator_top.class_indices)

train_data = np.load('bottleneck_feature_train.npy')
train_labels = to_categorical(generator_top.classes, num_classes=nb_classes)

generator_top2 = datagen_top.flow_from_directory(
    validation_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='categorical',
    shuffle=False)

validation_data = np.load('bottleneck_feature_validation.npy')
validation_labels = to_categorical(generator_top2.classes, num_classes=nb_classes)

model = Sequential()
model.add(GlobalAveragePooling2D(input_shape=train_data.shape[1:]))
model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes, activation='softmax'))

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

callbacks_list=[ModelCheckpoint(weight_path, monitor='val_acc', verbose=1, save_best_only=True),EarlyStopping(monitor='val_acc',patience=10,verbose=0)]



model.fit(train_data, train_labels, epochs=epochs, batch_size=batch_size,
          validation_data=(validation_data, validation_labels), callbacks=callbacks_list)

(eval_loss, eval_accuracy) = model.evaluate(
    validation_data, validation_labels, batch_size=batch_size, verbose=1)

print("[INFO] accuracy: {:.2f}%".format(eval_accuracy * 100))
print("[INFO] Loss: {}".format(eval_loss))


train_top_model()

微调代码：

from keras.applications.inception_v3 import InceptionV3, preprocess_input
from keras.preprocessing.image import ImageDataGenerator
from keras import optimizers
from keras.regularizers import l1_l2
from keras.models import Sequential, Model, model_from_json
from keras.layers import Dropout, GlobalAveragePooling2D, Dense
from keras.callbacks import ModelCheckpoint, EarlyStopping
import PIL
import math


weight_path = 'fine_tuned_weights.h5'
top_model_weight_path = 'top_model.h5'

img_width, img_height = (229, 229)

train_dir = 'Cancer_Data/Train'
validation_dir = 'Cancer_Data/Validate'

epochs = 150

batch_size = 128

nb_train_samples = 6454
nb_validation_samples = 1464

base_model =InceptionV3(weights= 'imagenet', include_top= False, input_shape=(229,229,3))
print "Model Loaded."

top_model= Sequential()
top_model.add(GlobalAveragePooling2D(input_shape=base_model.output_shape[1:]))
top_model.add(Dense(1024, activation='relu'))
top_model.add(Dense(8, activation= 'softmax'))

top_model.load_weights(top_model_weight_path)

model= Model(inputs= base_model.input, outputs= top_model(base_model.output))

for layer in model.layers[:172]:
    layer.trainable=False
for layer in model.layers[172:]:
    layer.trainable=True

model.compile(optimizer=optimizers.SGD(lr=0.0001, momentum=0.9),
          loss='categorical_crossentropy', metrics=['accuracy'])

train_datagen= ImageDataGenerator(
    preprocessing_function=preprocess_input,
    rotation_range=20,
    shear_range=0.3,
    zoom_range=0.3,
    horizontal_flip=True,
    vertical_flip=True)

test_datagen= ImageDataGenerator(preprocessing_function=preprocess_input)

train_generator= train_datagen.flow_from_directory(
    train_dir,
    target_size=(img_height,img_width),
    batch_size=batch_size,
    class_mode='categorical')

validation_generator= test_datagen.flow_from_directory(
    validation_dir,
    target_size=(img_height,img_width),
    batch_size=batch_size,
    class_mode='categorical')

callbacks_list=[ModelCheckpoint(weight_path, monitor='val_acc',verbose=1,save_best_only=True),
            EarlyStopping(monitor='val_acc',patience=10,verbose=0)]

model_json = model.to_json()
with open("fine_tuned_model.json", "w") as json_file:
    json_file.write(model_json)

model.fit_generator(
    train_generator,
    steps_per_epoch = int(math.ceil(nb_train_samples / batch_size)),
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps = int(math.ceil(nb_validation_samples / batch_size)), callbacks=callbacks_list)