为一动漫网站做一个图片搜索引擎，需要先定位动漫人物的脸，直接用opencv里的人脸检测API什么都框不出来，仔细想想也对，漫画里的人物没一个是正常的，眼睛都好大，鼻子几乎没有
，木法所以只好自己训练咯。
先安装TensorFlow object detection API，可以参考ubuntu16.04 TensorFlow目标检测API安装，等安装完成后，如果没有安装过tensorboard，最好顺便安装一下，以便观察loss等指标的变化
pip install tensorboard tensorboard --logdir /xxxx/model_ckpt/ # model_ckpt检查点的保存路径
一、准备数据集
tensorflow的目标检测有自己的格式，需要转换一下。首先需要一个图像标注软件，将我们数据集中每副图片的动漫脸标注出来，我使用的是labelImg，下载地址：
链接: https://pan.baidu.com/s/1i7oxr1r 密码: nkmz，解压后进入到\windows_v1.4.0\下运行labelImg.exe就ok了（需要python环境），打开图片后框出需要检测的目标，给一个标签，然后“保存”，labelImg保存的是一个个的XML文件，如此下去将训练集中的图片全部标注出来（一件没任何技术含量而且还很费时间的事情），两个小时后标注了100多张图片，暂时做测试足够了。
生成的XML文件如下：
<annotation> <folder>AIR</folder> <filename>吃团子可爱的神尾观铃.jpg</filename> <path>E:\code\image_search\image\人物\AIR\吃团子可爱的神尾观铃.jpg</path> <source> <database>Unknown</database> </source> <size> <width>800</width> <height>564</height> <depth>3</depth> </size> <segmented>0</segmented> <object> <name>person</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>382</xmin> <ymin>163</ymin> <xmax>572</xmax> <ymax>313</ymax> </bndbox> </object> </annotation>图片中标注了多少目标就会有几个<object>，然后开始转成tf 所需要的数据格式，具体格式说明请参考https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/using_your_own_dataset.md，这里我是先把xml转成了csv然后又转换成tf.record格式的
xml_metadata_csv.py
import os
import glob
import cv2
import numpy as np
import pandas as pd
import xml.etree.ElementTree as ET
def png_to_jpg(png_path):
jpg_path = png_path.replace('.png','.jpg')
im = cv2.imdecode(np.fromfile(png_path, dtype=np.uint8), -1)
cv2.imencode('.jpg', im)[1].tofile(jpg_path)
return jpg_path
def xml_to_csv(path):
xml_list = []
for dir in os.listdir(path):
img_dir = os.path.join(path, dir)
for xml_file in glob.glob(img_dir + '\*.xml'):
tree = ET.parse(xml_file)
root = tree.getroot()
file_name = root.find('path').text
# if file_name.find('.png') > 0:
# file_name = png_to_jpg(file_name)
for member in root.findall('object'):
value = (file_name,
int(root.find('size')[0].text),
int(root.find('size')[1].text), member[0].text,
int(member[4][0].text),
int(member[4][1].text),
int(member[4][2].text),
int(member[4][3].text)
)
xml_list.append(value)
column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']
xml_df = pd.DataFrame(xml_list, columns=column_name)
return xml_df
def main():
image_path = r'E:\code\MechineLeaning\image_search\CNN'
xml_df = xml_to_csv(image_path)
xml_df.to_csv('CSVMETADATAFILE.csv', index=None)
print('successfully converted xml metadata to csv')
if __name__ == '__main__':
main()
png_to_jpg()需要注意，这个是python3写带中文路径图片的一个处理方法，不能直接用cv2.write()
csv转tf.record，generate_tfrecord.py
from __future__ import division
from __future__ import print_function
from __future__ import absolute_import
import os
import io
import pandas as pd
import tensorflow as tf
from PIL import Image
from collections import namedtuple
import dataset_util
import sys
# reload(sys)
# sys.setdefaultencoding('utf-8')
flags = tf.app.flags
flags.DEFINE_string('csv_input', 'CSVMETADATAFILE.csv', 'Path to the CSV input')
flags.DEFINE_string('output_path', 'person_val.record', 'Path to output TFRecord')
FLAGS = flags.FLAGS
# 将标签转换成对应的数值，从1开始
def class_text_to_int(row_label):
if row_label == 'person':
return 1
else:
None
def split(df, group):
data = namedtuple('data', ['filename', 'object'])
gb = df.groupby(group)
return [data(filename, gb.get_group(x)) for filename, x in zip(gb.groups.keys(), gb.groups)]
def create_tf(group):
with tf.gfile.GFile(group.filename, 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = Image.open(encoded_jpg_io)
width, height = image.size
filename = group.filename.encode('utf8')
image_format = b'jpg'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
for index, row in group.object.iterrows():
xmins.append(row['xmin'] / width)
xmaxs.append(row['xmax'] / width)
ymins.append(row['ymin'] / height)
ymaxs.append(row['ymax'] / height)
classes_text.append(row['class'].encode('utf8'))
classes.append(class_text_to_int(row['class']))
tf_example = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(filename),
'image/source_id': dataset_util.bytes_feature(filename),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
}))
return tf_example
def main(_):
writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
# path = os.path.join(os.getcwd(), path_images)
examples = pd.read_csv(FLAGS.csv_input)
grouped = split(examples, 'filename')
for group in grouped:
tf_example = create_tf(group)
writer.write(tf_example.SerializeToString())
writer.close()
output_path = os.path.join(os.getcwd(), FLAGS.output_path)
print('Successfully created the TFRecords: {}'.format(output_path))
if __name__ == '__main__':
tf.app.run()二、使用tf object detection API
在安装好API后的object_detection目录下有好几个py文件，使用train.py来进行模型训练，tf给出的调用例子：
Example usage: ./train \ --logtostderr \ --train_dir=path/to/train_dir \ --model_config_path=model_config.pbtxt \ --train_config_path=train_config.pbtxt \ --input_config_path=train_input_config.pbtxt所以我们还需要准备运行train.py需要的三个文件，分别是 model_config.pbtxt、train_config.pbtxt、train_input_config.pbtxt
还有一种调用方式，是配置一个pipeline_config.pbtxt文件，其实就是把上面的三个文件写在一个文件里面了，我是为了清晰点所以写了三个文件。
model_config.pbtxt
ssd {
num_classes: 1
box_coder {
faster_rcnn_box_coder {
y_scale: 10.0
x_scale: 10.0
height_scale: 5.0
width_scale: 5.0
}
}
matcher {
argmax_matcher {
matched_threshold: 0.5
unmatched_threshold: 0.5
ignore_thresholds: false
negatives_lower_than_unmatched: true
force_match_for_each_row: true
}
}
similarity_calculator {
iou_similarity {
}
}
anchor_generator {
ssd_anchor_generator {
num_layers: 6
min_scale: 0.2
max_scale: 0.95
aspect_ratios: 1.0
aspect_ratios: 2.0
aspect_ratios: 0.5
aspect_ratios: 3.0
aspect_ratios: 0.3333
}
}
image_resizer {
fixed_shape_resizer {
height: 300
width: 300
}
}
box_predictor {
convolutional_box_predictor {
min_depth: 0
max_depth: 0
num_layers_before_predictor: 0
use_dropout: false
dropout_keep_probability: 0.8
kernel_size: 1
box_code_size: 4
apply_sigmoid_to_scores: false
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,
scale: true,
center: true,
decay: 0.9997,
epsilon: 0.001,
}
}
}
}
feature_extractor {
type: 'ssd_mobilenet_v1'
min_depth: 16
depth_multiplier: 1.0
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,
scale: true,
center: true,
decay: 0.9997,
epsilon: 0.001,
}
}
}
loss {
classification_loss {
weighted_sigmoid {
anchorwise_output: true
}
}
localization_loss {
weighted_smooth_l1 {
anchorwise_output: true
}
}
hard_example_miner {
num_hard_examples: 3000
iou_threshold: 0.99
loss_type: CLASSIFICATION
max_negatives_per_positive: 3
min_negatives_per_image: 0
}
classification_weight: 1.0
localization_weight: 1.0
}
normalize_loss_by_num_matches: true
post_processing {
batch_non_max_suppression {
score_threshold: 1e-8
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 100
}
score_converter: SIGMOID
}
}train_config.pbtxt
batch_size: 24
optimizer {
rms_prop_optimizer: {
learning_rate: {
exponential_decay_learning_rate {
initial_learning_rate: 0.004
decay_steps: 800720
decay_factor: 0.95
}
}
momentum_optimizer_value: 0.9
decay: 0.9
epsilon: 1.0
}
}
fine_tune_checkpoint: "/home/bqh/Code/image_search/model_ckpt/model.ckpt"
from_detection_checkpoint: false
# Note: The below line limits the training process to 200K steps, which we
# empirically found to be sufficient enough to train the pets dataset. This
# effectively bypasses the learning rate schedule (the learning rate will
# never decay). Remove the below line to train indefinitely.
num_steps: 200000
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
ssd_random_crop {
}
}train_input_config.pbtxt
tf_record_input_reader {
input_path: "$PATH/train.record"
}
label_map_path: "$PATH/label_map.pbtxt"
说明：在model_config文件中，有一项 num_classes: 1，因为这里训练的只是找出图片中的漫画人物的脸所以就一个类别，如果检测的是多目标的话，有几项这里就改成几；这里使用的是SSD检测模型也可以使用别的检测模型，比如faster rcnn（理论请参考
http://blog.csdn.net/luoyang224/article/details/77529536）；train_input_config文件中又多出来两个文件的路径，分别是第一步生成的训练集路径和训练集中目标的标签
label_map.pbtxt
item{
id:1
name:'person'
}三、开始训练
我手头没有可供规模大点的数据集使用的GPU，所以就直接在CPU上训练的，不过速度真的太慢了，按照上面的配置文件每个batch 24长图片，大概需要16G的内存，我这里训练了四天多才迭代了进8W次。如果有条件的话还是使用GPU吧！运行命令：python train.py --logtostderr --train_dir=$PATH/model_ckpt --model_config_path=$PATH/config/model_config.pbtxt --train_config_path=$PATH/config/train_config.pbtxt --input_config_path=$PATH/config/train_input_config.pbtxt
四、检测
在API里有个文件export_inference_graph.py可以导出模型，但是运行的时候报错，在网上查了下说是因为TF的版本问题，反正不导出也OK，就直接测试吧。使用eval.py，运行的格式和上面train.py差不多：
python eval.py --logtostderr --checkpoint_dir=$PATH/model_ckpt --eval_dir=$PATH/eval_dir --eval_config_path=$PATH/config/eval_config.pbtxt --model_config_path=$PATH/config/model_config.pbtxt --input_config_path=$PATH/config/eval_input_config.pbtxt
同样需要准备eval_config.pbtxt、eval_input_config.pbtxt文件
eval_config.pbtxt
num_examples: 2000 # Note: The below line limits the evaluation process to 10 evaluations. # Remove the below line to evaluate indefinitely. # max_evals: 10eval_input_config.pbtxt
tf_record_input_reader {
input_path: "$PATH/person_val.record"
}
label_map_path: "$PATH/eval_label_map.pbtxt"
shuffle: false
num_readers: 1这里的person_val.record是测试集的tf.record文件，生成方法同第一步；eval_label_map.pbtxt文件同第一步的label_map.pbtxt文件。这里遇见一个问题，源码的utils/object_detection_evaluation.py文件中的第433行有个判断
if groundtruth_is_difficult_list is None:但是没有判断groundtruth_is_difficult_list 是空的情况，导致groundtruth_is_difficult_list变量没有赋值，后续在utils/per_image_evaluation.py的202行调用的时候会报错，没继续研究下去到底是我配置的问题还是源码这里应该判断一次，我把utils/object_detection_evaluation.py的433行改成了：
if groundtruth_is_difficult_list is None or len(groundtruth_is_difficult_list) == 0:再运行就没问题了。运行后在$PATH/eval_dir目录下会生成out文件，然后打开tensorboard
tensorboard -log $PATH/eval_dir/在浏览器中查看
可以看到已经把结果显示出来的，之所以有偏差是因为还在训练当中，train.py还没收敛到一个满意的loss，还有就是训练集数据量太少，需要加大样本量，不过已经看到结果了。对于我的图片搜索来说，已经可以区分出图片中是否有人脸啦！
五、模型导出
如同上面说的，直接使用
python export_inference_graph.py --input_type image_tensor --pipeline_config_path $PATH/config/ttadm_ssd_inception.config --trained_checkpoint_prefix $PATH/model_ckpt/model.ckpt-* --output_directory $PATH/exported_model_directory
exporter.py 71行会报错，
rewrite_options = rewriter_config_pb2.RewriterConfig(optimize_tensor_layout=True)
修改为：
rewrite_options = rewriter_config_pb2.RewriterConfig()
六、执行预测
import cv2
import numpy as np
import tensorflow as tf
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
class TOD(object):
def __init__(self):
self.PATH_TO_CKPT = r'$PATH/exported_model_directory/frozen_inference_graph.pb'
self.PATH_TO_LABELS = r'$PATH/eval_label_map.pbtxt'
self.NUM_CLASSES = 1
self.detection_graph = self._load_model()
self.category_index = self._load_label_map()
def _load_model(self):
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(self.PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
return detection_graph
def _load_label_map(self):
label_map = label_map_util.load_labelmap(self.PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map,
max_num_classes=self.NUM_CLASSES,
use_display_name=True)
category_index = label_map_util.create_category_index(categories)
return category_index
def detect(self, image):
with self.detection_graph.as_default():
with tf.Session(graph=self.detection_graph) as sess:
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image, axis=0)
image_tensor = self.detection_graph.get_tensor_by_name('image_tensor:0')
boxes = self.detection_graph.get_tensor_by_name('detection_boxes:0')
scores = self.detection_graph.get_tensor_by_name('detection_scores:0')
classes = self.detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = self.detection_graph.get_tensor_by_name('num_detections:0')
# Actual detection.
(boxes, scores, classes, num_detections) = sess.run(
[boxes, scores, classes, num_detections],
feed_dict={image_tensor: image_np_expanded})
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(
image,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
self.category_index,
use_normalized_coordinates=True,
line_thickness=8)
cv2.namedWindow("detection", cv2.WINDOW_NORMAL)
cv2.imshow("detection", image)
cv2.waitKey(0)
def main():
image = cv2.imread('1.jpg')
detecotr = TOD()
detecotr.detect(image)
pass
if __name__ == '__main__':
main()