ubuntu下谷歌开源的TensorFlow Object Detection API的安装教程

环境

Ubuntu16.04/anaconda+tensorflow(gpu)1.4.0+python=3.5

下载

tensorflow model

估计下载的很慢，提供一个百度云链接：https://pan.baidu.com/s/1EB1VLj5Znw_exAAUa1ftIg 密码：2o0a

直接下载整个文件就行了，因为后面要在jupyter notebook中运行，所以直接放在了jupyter notebook的工作目录里面(关于工作目录的配置我也写过，看一下就可以了)，我的工作目录是Documents/jworkplace/

cd Documents/jworkplace/
unzip models-master.zip

安装

官方教程，其实教程就在这个文件里面models/research/object_detection/g3doc/installation.md(可以在github直接观看) 。

1.依赖

这里面需要安装的依赖

Protobuf
Pillow
lxml
Jupyter notebook
Matplotlib
Tensorflow

命令安装依赖

source activate tensorflow
conda install Protobuf
conda install lxml
conda install matplotlib
conda install pillow

2.编译

继续上面，使用Protobuf编译一下，需要在object_detection所在的父目录下进行及research下，

cd Documents/jworkplace/models-master/research/
protoc object_detection/protos/*.proto --python_out=.

不输出任何东西就可以了，输出这个Missing output directives也不行。

3.添加环境变量

格式是这样的

# From tensorflow/models/research/
export PYTHONPATH=$PYTHONPATH:`pwd`:`pwd`/slim

首先代开~/.bashrc

sudo gedit ~/.bashrc

然后在后面添加

export PYTHONPATH=$PYTHONPATH:/home/pc314/Documents/jworkplace/models-master/research:/home/pc314/Documents/jworkplace/models-master/research/slim

4.测试

代开jupyter notebook的话，应该会有models-master文件，打开models-master/research/object_detection/object_detection_tutorial.ipynb

然后点击Cell->Run all应该就可以了。正常的话会出现两张图。

(1)然而我运行这个的时候出现了

ImportError: No module named 'object_detection'

具体的解决方法是

打开/home/pc314/anaconda3/envs/tensorflow/lib/python3.5/site-packages，在这个目录下添加一个tensorflow_model.pth，里面的内容写上

/home/pc314/Documents/jworkplace/models-master/research
/home/pc314/Documents/jworkplace/models-master/research/slim

(2).ImportError: No module named 'utils'

pip install utils

这样子就可以了

(2)还有一个就是代码没有对齐，里面有一个最大的一个cell里面的代码，我这里面贴出来(省下时间)

def run_inference_for_single_image(image, graph):with graph.as_default():with tf.Session() as sess:# Get handles to input and output tensorsops = tf.get_default_graph().get_operations()all_tensor_names = {output.name for op in ops for output in op.outputs}tensor_dict = {}for key in ['num_detections', 'detection_boxes', 'detection_scores','detection_classes', 'detection_masks']:tensor_name = key + ':0'if tensor_name in all_tensor_names:tensor_dict[key] = tf.get_default_graph().get_tensor_by_name(tensor_name)if 'detection_masks' in tensor_dict:# The following processing is only for single imagedetection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0])detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0])# Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32)detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1])detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1])detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(detection_masks, detection_boxes, image.shape[0], image.shape[1])detection_masks_reframed = tf.cast(tf.greater(detection_masks_reframed, 0.5), tf.uint8)# Follow the convention by adding back the batch dimensiontensor_dict['detection_masks'] = tf.expand_dims(detection_masks_reframed, 0)image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0')# Run inferenceoutput_dict = sess.run(tensor_dict,feed_dict={image_tensor: np.expand_dims(image, 0)})# all outputs are float32 numpy arrays, so convert types as appropriateoutput_dict['num_detections'] = int(output_dict['num_detections'][0])output_dict['detection_classes'] = output_dict['detection_classes'][0].astype(np.uint8)output_dict['detection_boxes'] = output_dict['detection_boxes'][0]output_dict['detection_scores'] = output_dict['detection_scores'][0]if 'detection_masks' in output_dict:output_dict['detection_masks'] = output_dict['detection_masks'][0]return output_dict