tensorflow object detection API 训练数据集
1. API的安装
官方github地址
下载object_detection和slim文件内容
安装可参照官方文档
2. 制作tfrecord数据集
a. voc2007_to_tfrecord
首先制作voc数据集 通过dataset_tools/create_pascal_tf_record.py进行转换
# Copyright 2017 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Convert raw PASCAL dataset to TFRecord for object_detection.
Example usage:
#下方代码用于生产tfrecord文件，根据文件目录相应调整。
python create_pascal_tf_record.py --data_dir=/home/huazhe/VOCdevkit --year=VOC2007 --output_path=pascal.record
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import hashlib
import io
import logging
import os
from lxml import etree
import PIL.Image
import tensorflow as tf
from object_detection.utils import dataset_util
from object_detection.utils import label_map_util
flags = tf.app.flags
flags.DEFINE_string('data_dir', '', 'Root directory to raw PASCAL VOC dataset.')
flags.DEFINE_string('set', 'train', 'Convert training set, validation set or '
'merged set.')
flags.DEFINE_string('annotations_dir', 'Annotations',
'(Relative) path to annotations directory.')
flags.DEFINE_string('year', 'VOC2007', 'Desired challenge year.')
flags.DEFINE_string('output_path', '', 'Path to output TFRecord')
flags.DEFINE_string('label_map_path', 'person_label_map.pbtxt',
'Path to label map proto') #person_label_map.pbtxt文件位置调整
flags.DEFINE_boolean('ignore_difficult_instances', False, 'Whether to ignore '
'difficult instances')
FLAGS = flags.FLAGS
SETS = ['train', 'val', 'trainval', 'test']
YEARS = ['VOC2007', 'VOC2012', 'merged']
def dict_to_tf_example(data,
dataset_directory,
label_map_dict,
ignore_difficult_instances=False,
image_subdirectory='JPEGImages'):
"""Convert XML derived dict to tf.Example proto.
Notice that this function normalizes the bounding box coordinates provided
by the raw data.
Args:
data: dict holding PASCAL XML fields for a single image (obtained by
running dataset_util.recursive_parse_xml_to_dict)
dataset_directory: Path to root directory holding PASCAL dataset
label_map_dict: A map from string label names to integers ids.
ignore_difficult_instances: Whether to skip difficult instances in the
dataset (default: False).
image_subdirectory: String specifying subdirectory within the
PASCAL dataset directory holding the actual image data.
Returns:
example: The converted tf.Example.
Raises:
ValueError: if the image pointed to by data['filename'] is not a valid JPEG
"""
img_path = os.path.join('VOC2007', image_subdirectory, data['filename']) #调整对应图片存放路径
full_path = os.path.join(dataset_directory, img_path)
with tf.gfile.GFile(full_path, 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = PIL.Image.open(encoded_jpg_io)
if image.format != 'JPEG':
raise ValueError('Image format not JPEG')
key = hashlib.sha256(encoded_jpg).hexdigest()
width = int(data['size']['width'])
height = int(data['size']['height'])
xmin = []
ymin = []
xmax = []
ymax = []
classes = []
classes_text = []
truncated = []
poses = []
difficult_obj = []
if 'object' in data:
for obj in data['object']:
difficult = bool(int(obj['difficult']))
if ignore_difficult_instances and difficult:
continue
difficult_obj.append(int(difficult))
xmin.append(float(obj['bndbox']['xmin']) / width)
ymin.append(float(obj['bndbox']['ymin']) / height)
xmax.append(float(obj['bndbox']['xmax']) / width)
ymax.append(float(obj['bndbox']['ymax']) / height)
classes_text.append(obj['name'].encode('utf8'))
classes.append(label_map_dict[obj['name']])
truncated.append(int(obj['truncated']))
poses.append(obj['pose'].encode('utf8'))
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(
data['filename'].encode('utf8')),
'image/source_id': dataset_util.bytes_feature(
data['filename'].encode('utf8')),
'image/key/sha256': dataset_util.bytes_feature(key.encode('utf8')),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmin),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmax),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymin),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymax),
'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
'image/object/difficult': dataset_util.int64_list_feature(difficult_obj),
'image/object/truncated': dataset_util.int64_list_feature(truncated),
'image/object/view': dataset_util.bytes_list_feature(poses),
}))
return example
def main(_):
if FLAGS.set not in SETS:
raise ValueError('set must be in : {}'.format(SETS))
if FLAGS.year not in YEARS:
raise ValueError('year must be in : {}'.format(YEARS))
data_dir = FLAGS.data_dir
years = ['VOC2007', 'VOC2012']
if FLAGS.year != 'merged':
years = [FLAGS.year]
writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)
for year in years:
logging.info('Reading from PASCAL %s dataset.', year)
examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
FLAGS.set + '.txt') #对应到相应txt文件
annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
examples_list = dataset_util.read_examples_list(examples_path)
for idx, example in enumerate(examples_list):
if idx % 100 == 0:
logging.info('On image %d of %d', idx, len(examples_list))
path = os.path.join(annotations_dir, example + '.xml')
with tf.gfile.GFile(path, 'r') as fid:
xml_str = fid.read()
xml = etree.fromstring(xml_str)
data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']
tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
FLAGS.ignore_difficult_instances)
writer.write(tf_example.SerializeToString())
writer.close()
if __name__ == '__main__':
tf.app.run()b. tfrecord制作
首先通过xml_to_csv.py将数据集转换为csv文件，让后通过generate_tfrecord.py生成tfrecord。
3. 训练准备
a. 下载预训练模型
b. config文件修改
在sample/configs/下
# Faster R-CNN with Inception v2, configuration for MSCOCO Dataset.
# Users should configure the fine_tune_checkpoint field in the train config as
# well as the label_map_path and input_path fields in the train_input_reader and
# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
# should be configured.
model {
faster_rcnn {
num_classes: 1 # 修改这里 改成自己的类数
image_resizer {
keep_aspect_ratio_resizer {
min_dimension: 600
max_dimension: 1024
}
}
feature_extractor {
type: 'faster_rcnn_inception_v2'
first_stage_features_stride: 16
}
first_stage_anchor_generator {
grid_anchor_generator {
scales: [0.25, 0.5, 1.0, 2.0]
aspect_ratios: [0.5, 1.0, 2.0]
height_stride: 16
width_stride: 16
}
}
first_stage_box_predictor_conv_hyperparams {
op: CONV
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
truncated_normal_initializer {
stddev: 0.01
}
}
}
first_stage_nms_score_threshold: 0.0
first_stage_nms_iou_threshold: 0.7
first_stage_max_proposals: 300
first_stage_localization_loss_weight: 2.0
first_stage_objectness_loss_weight: 1.0
initial_crop_size: 14
maxpool_kernel_size: 2
maxpool_stride: 2
second_stage_box_predictor {
mask_rcnn_box_predictor {
use_dropout: false
dropout_keep_probability: 1.0
fc_hyperparams {
op: FC
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
variance_scaling_initializer {
factor: 1.0
uniform: true
mode: FAN_AVG
}
}
}
}
}
second_stage_post_processing {
batch_non_max_suppression {
score_threshold: 0.0
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 300
}
score_converter: SOFTMAX
}
second_stage_localization_loss_weight: 2.0
second_stage_classification_loss_weight: 1.0
}
}
# 这部分为对训练过程进行微调
train_config: {
# batch_size 可根据自己的显存大小调整
batch_size: 1
optimizer {
momentum_optimizer: {
learning_rate: {
manual_step_learning_rate {
initial_learning_rate: 0.0002
schedule {
step: 900000
learning_rate: .00002
}
schedule {
step: 1200000
learning_rate: .000002
}
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
gradient_clipping_by_norm: 10.0
fine_tune_checkpoint: "faster_rcnn_inception_v2_coco_2018_01_28/model.ckpt"#对应到下载模型地址
from_detection_checkpoint: true#使用迁移学习
# Note: The below line limits the training process to 200K steps, which we
# empirically found to be sufficient enough to train the COCO 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 {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "train.record"# train.record路径
}
label_map_path: "label_map.pbtxt"## .pptxt文件地址
}
eval_config: {
num_examples: 1000
# Note: The below line limits the evaluation process to 10 evaluations.
# Remove the below line to evaluate indefinitely.
max_evals: 10
}
eval_input_reader: {
tf_record_input_reader {
input_path: "val.record"
}
label_map_path: "label_map.pbtxt"
shuffle: false
num_readers: 1
}c. .pbtxt文件
#内容如下 data/文件夹下有模板
item {
id: 1
name: 'person'
}4. 训练模型
a. model_main .py
python object_detection/model_main.py #model_main.py 对应位置
--alsologtostderr \
--pipeline_config_path=faster_rcnn_resnet50_coco.config \ #config文件对应位置
--model_dir=save_model \ #训练模型储存位置
--num_train_steps=50000 \
--num_eval_steps=2000b. train .py(旧版 legacy/)
python object_detection\legacy\train.py
--logtostderr \
--train_dir=save_model \ #模型保存位置
--pipeline_config_path=faster_rcnn_inception_v2_coco.config #对应config位置5. tesorboard
tensorboard --logdir=model #model 位置6. 模型转换
python export_inference_graph.py \
--input_type image_tensor \
--pipeline_config_path ssd_mobilenet_v1_coco.config \ --trained_checkpoint_prefix model.ckpt-100000 \ #这里要根据自己训练的次数修改model.ckpt-10000的数字
--output_directory person_inference_graph #输入转换后保存模型的地址