Tensorflow Object Detection API使用

安裝

安裝tensorflow-gpu

最新版的tensorflow不支援cuda8.0， 是以，這裡安裝了tensorflow1.4，用清華的鏡像：

pip install \

-i https://pypi.tuna.tsinghua.edu.cn/simple/ \

https://mirrors.tuna.tsinghua.edu.cn/tensorflow/linux/gpu/tensorflow_gpu-1.4.0-cp27-none-linux_x86_64.whl

擷取 TensorFlow Models 源碼：

git clone https://github.com/tensorflow/models –recursive

cd models/

安裝必要的python包，如pillow，lxml，jupyter，matplotlib

手動編譯安裝Protobuf 3.3：

wget https://github.com/google/protobuf/archive/v3.3.0.tar.gz

tar zxvf v3.3.0.tar.gz

cd protobuf-3.3.0/

./autogen.sh

./configure

make -j8

make install

如果出錯，configure.ac:17: error: possibly undefined macro: AC_PROG_LIBTOOL，則安裝sudo apt-get install libtool

添加環境變量export LD_LIBRARY_PATH=/usr/local/lib

編譯proto:

(Folder tensorflow/models/research)

protoc object_detection/protos/*.proto –python_out=.

export PYTHONPATH=$PYTHONPATH:

pwd

:

pwd

/slim

測試是否成功

python object_detection/builders/model_builder_test.py

Ran 13 tests in 0.045s

OK

http://mp.weixin.qq.com/s/eN41M1sMLxvQMEl0IhyC9w

準備資料集，并轉成tfrecords, 利用腳本create_pet_tf_record.py即可，需要調整資料目錄

• images
• annotations
  • xmls
  • trainval.txt

python create_pet_tf_record.py –data_dir=../../Deep-Learning-master/tensorflow_toy_detector –output_dir=../../Deep-Learning-master/tensorflow_toy_detector –label_map_path=../../Deep-Learning-master/tensorflow_toy_detector/toy_label_map.pbtxt

其中，label_map是item { id: 1 name: ‘toy’}

修改配置檔案，object_detection/samples/configs,修改num以及路徑

訓練模型，我一開始用虛拟機訓練，可能記憶體不夠，程式直接被kill了，換到gpu上就可以了。另外，注意要先删掉logs，否則總是從上一次恢複運作。

錯誤：local variable ‘total_loss’ referenced before assignment

似乎是一個bug，可以直接在/usr/lib/python2.7/site-packages/tensorflow/contrib/slim/python/slim/learning.py那裡把total_loss=None

錯誤：:Caught OutOfRangeError. Stopping Training.

檢查下dataset的路徑是否錯誤

python train.py --train_dir=../../../toy/Deep-Learning-master/tensorflow_toy_detector/logs/  --pipeline_config_path=../../../toy/Deep-Learning-master/tensorflow_toy_detector/faster_rcnn_resnet101_coco.config
           

測試模型eval.py

可以用tensorboard –logdir=eval_logs檢視訓練結果

将訓練好的模型導出，産生.pb的模型檔案，儲存在output檔案夾中

python export_inference_graph.py --input_type=image_tensor --pipeline_config_path=../../../toy/Deep-Learning-master/tensorflow_toy_detector/faster_rcnn_resnet101_coco.config --trained_checkpoint_prefix=../../../toy/Deep-Learning-master/tensorflow_toy_detector/logs/model.ckpt- --output_directory ../../../toy/Deep-Learning-master/tensorflow_toy_detector/output
           

使用儲存好的模型對圖檔進行物體檢測

我寫了一個腳本detection_pic.py：

import tensorflow as tf
from PIL import Image
import numpy as np

from utils import label_map_util
from utils import visualization_utils as vis_util


PATH_TO_CKPT = '.pb'
PATH_TO_LABELS = ''
NUM_CLASS = 

flags = tf.app.flags
flags.DEFINE_string('ckpt_path', '', 'ckpt path')
flags.DEFINE_integer('num_class', , 'number of classes')
flags.DEFINE_string('label_path', '', 'label path')
flags.DEFINE_string('image_path', '', 'image path')

FLAGS = flags.FLAGS

def load_image_into_numpy_array(image):
    (im_width, im_height) = image.size
    return np.array(image.getdata()).reshape(
        (im_height, im_width, )).astype(np.uint8)

def main(_):
    ckpt_path = FLAGS.ckpt_path
    num_class = FLAGS.num_class
    label_path = FLAGS.label_path
    image_path = FLAGS.image_path

    # load tensorflow model into memory
    detection_graph = tf.Graph()
    with detection_graph.as_default():
        od_graph_def = tf.GraphDef()
        with tf.gfile.GFile(ckpt_path, 'rb') as fid:
            serialized_graph = fid.read()
            od_graph_def.ParseFromString(serialized_graph)
            tf.import_graph_def(od_graph_def, name='')

    # load label map
    label_map = label_map_util.load_labelmap(label_path)
    categories = label_map_util.convert_label_map_to_categories(label_map,
                                                                max_num_classes=num_class,
                                                                use_display_name=True)
    category_index = label_map_util.create_category_index(categories)

    # detection
    with detection_graph.as_default():
        with tf.Session(graph=detection_graph) as sess:
            image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
            detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')

            detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
            detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
            num_detections = detection_graph.get_tensor_by_name('num_detections:0')

            image = Image.open(image_path)
            image_np = load_image_into_numpy_array(image)
            image_np_expanded = np.expand_dims(image_np, axis=)

            # Actial detection
            (boxes, scores, classes, num) = sess.run(
                [detection_boxes, detection_scores, detection_classes, num_detections],
                feed_dict={image_tensor: image_np_expanded}
            )
            vis_util.visualize_boxes_and_labels_on_image_array(
                image_np,
                np.squeeze(boxes),
                np.squeeze(classes).astype(np.int32),
                np.squeeze(scores),
                category_index,
                use_normalized_coordinates=True,
                line_thickness=
            )
            output_image = Image.fromarray(image_np)
            output_image.save('out.jpeg')

if __name__ == '__main__':
  tf.app.run()
           

運作以下指令：

python detection_pic.py --ckpt_path=../../../toy/Deep-Learning-master/tensorflow_toy_detector/output/frozen_inference_graph.pb --num_class= --label_path=../../../toy/Deep-Learning-master/tensorflow_toy_detector/toy_label_map.pbtxt --image_path=../../../toy/Deep-Learning-master/tensorflow_toy_detector/images/toy11.jpg