颜值打分器

颜值打分器

最近，华南理工大学发布了一个颜值数据库SCUT-FBP5500 <https://arxiv.org/abs/1801.06345>
，数据集共有5500个人，分值在1~5之间，

数据库下载地址：

* 百度网盘:https://pan.baidu.com/s/1gguqPpx <https://pan.baidu.com/s/1gguqPpx>
，密码是mh8j
* GoogleDrive:
https://drive.google.com/open?id=1_BBiG0xOxYnCTItUXh82GTVorp6ODy-m
<https://drive.google.com/open?id=1_BBiG0xOxYnCTItUXh82GTVorp6ODy-m>



我将利用keras建立一个基于深度学习的颜值打分系统，不同于图像分类任务，颜值打分是一个回归任务，不能利用keras自带的ImageDatagenerator产生迭代器给模型喂数据，我们将实现一个类似的迭代器
__author__ = 'lzy' # image_input.py import cv2 from keras.utils import Sequence
import math import numpy as np from random import shuffle, randint import os
class SequenceData(Sequence): def __init__(self, file_list, batch_size,
target_size, mode='caffe'): self.file_list = file_list self.batch_size =
batch_size self.target_size = target_size self.mode = modedef __len__(self):
num_imgs = len(self.file_list)return math.ceil(num_imgs / self.batch_size) def
__getitem__(self, idx): file_sub_list = self.file_list[idx*self.batch_size :
(idx+1)*self.batch_size] batch_x = np.array([self.read_img(file[0]) for file in
file_sub_list]) batch_y = np.array([file[1] for file in file_sub_list],
dtype=np.float32)return batch_x, batch_y def read_img(self, file_name):
file_path = os.path.join('data/Images', file_name) try: img =
cv2.imread(file_path) img = cv2.resize(img, self.target_size)# 象征性的做一点数据增广 #
随机对图像进行数据翻转 if randint(0, 1): img = img[:, ::-1, :] img = np.array(img,
dtype=np.float32)if self.mode == 'caffe': img[:, :, 0] -= 103.939 img[:, :, 1]
-=116.779 img[:, :, 2] -= 123.68 elif self.mode == 'tf': img =
cv2.cvtColor(img, cv2.COLOR_BGR2RGB) img = img /127.5 - 1.0 except Exception as
e: print(e)else: return img def read_file_list(train_test_split_ratio=0.8): with
open('data/train_test_files/SCUT-FBP5500.txt', 'r') as f: file_list = f.read()
file_list = file_list.split('\n')[:-1] file_list = [file.split(' ') for file in
file_list]# 将颜值分数归一化到[0, 1]之间 file_list = [(file[0], 0.2 * float(file[1])) for
filein file_list] shuffle(file_list) train_len = int(len(file_list) *
train_test_split_ratio) train_file_list = file_list[:train_len] test_file_list
= file_list[train_len:]return train_file_list, test_file_list if __name__ ==
'__main__': read_file_list()
keras已经提供了好多个在Imagenet上训练过的模型，我们将采用这些预训练模型来建议一个颜值打分系统
__author__ = 'lzy' import tensorflow as tf from keras.applications import
ResNet50from keras import optimizers from keras.models import Sequential from
keras.layersimport Dense, Dropout from keras.callbacks import EarlyStopping,
ReduceLROnPlateau, ModelCheckpointfrom keras.backend.tensorflow_backend import
set_sessionimport math import os from image_input import SequenceData,
read_file_list# 指定gpu和显存占用, stupid tensorflow os.environ['CUDA_VISIBLE_DEVICES'
] ='1' config = tf.ConfigProto() config.gpu_options.allow_growth = True
set_session(tf.Session(config=config)) batch_size =32 target_size = (224, 224)
# 这个例子中我们采用resnet50作为base network resnet = ResNet50(include_top=False, pooling=
'avg') resnet.trainable = False model = Sequential() model.add(resnet)
model.add(Dropout(0.5)) # 加个dropout防止过拟合 model.add(Dense(1, activation='sigmoid'
))# 增加一层给颜值打分，激活函数选择为sigmoid保证输出在[0, 1]之间 print(model.summary())
model.compile(optimizer=optimizers.SGD(lr=0.001), loss='mse') callbacks =
[EarlyStopping(monitor='val_loss', patience=5, verbose=1, min_delta=1e-4),
ReduceLROnPlateau(monitor='val_loss', patience=3, factor=0.1, epsilon=1e-4),
ModelCheckpoint(monitor='val_loss', filepath='weights/resnet50_weights.hdf5',
save_best_only=True, save_weights_only=True)] train_file_list, test_file_list =
read_file_list() train_steps_per_epoch = math.ceil(len(train_file_list) /
batch_size) test_steps_per_epoch = math.ceil(len(test_file_list) / batch_size)
train_data = SequenceData(train_file_list, batch_size, target_size) test_data =
SequenceData(test_file_list, batch_size, target_size)
model.fit_generator(train_data, steps_per_epoch=train_steps_per_epoch, epochs=30
, verbose=1, callbacks=callbacks, validation_data=test_data,
validation_steps=test_steps_per_epoch, use_multiprocessing=True)
训练结束就来测试一下吧，
__author__ = 'lzy' from keras.applications import ResNet50 from keras.models
import Sequential from keras.layers import Dense import numpy as np import os
import cv2 def score(model, img_path, target_size=(224, 224), mode='caffe'):
img = cv2.imread(img_path) img = cv2.resize(img, target_size) img =
np.array(img, dtype=np.float32)if mode == 'caffe': img[:, :, 0] -= 103.939
img[:, :,1] -= 116.779 img[:, :, 2] -= 123.68 elif mode == 'tf': img =
cv2.cvtColor(img, cv2.COLOR_BGR2RGB) img = img /127.5 - 1.0 img =
np.expand_dims(img, axis=0) scores = model.predict_on_batch(img) print(scores)
os.environ['CUDA_VISIBLE_DEVICES'] = '1' target_size = (224, 224) resnet =
ResNet50(include_top=False, pooling='avg') model = Sequential()
model.add(resnet) model.add(Dense(1, activation='sigmoid')) model.trainable =
False model.load_weights('weights/resnet50_weights.hdf5') score(model,
'data/Images/test.jpg')
搞一张大幂幂的头像来评一下：

竟然得到了4.29这么高的分数

再来试试程序员共同的老婆Gakki吧：
哎，老婆只得到了3.76分，不过这已经比80%的人都好看了

输给了大幂幂，这个系统一定把欧派也考虑在内了，不正经的CNN

最后再来看看我自己能得到多少分

只能告诉你们我和吴彦祖的平均分是3.53，搞什么搞嘛

• « 上一篇：用Python解锁“吃鸡”正确姿势
• » 下一篇：程序员必须掌握的100个英语单词