Tensorflow目标检测API在Windows10环境下进行配置

官方地址：目标检测API下载

Tensorflow Object Detection API

配置过程

Tensorflow 安装/查找所在目录

安装：

# For CPU
$ pip install tensorflow
# For GPU version
$ pip install tensorflow-gpu

查询所在目录：

$ python
import tensorflow as tf
tf.__path__

下载Tensorflow Models

切换到 Tensorflow 目录下进行下载

# from <path to tensorflow>
$ git clone https://github.com/tensorflow/models.git

安装相关依赖库

$ pip install Cython,contextlib2,jupyter,matplotlib,pillow,lxml,

编译protobuf

# cmd
# From <path to tensorflow>/models/research/ [切换到相关目录]
$ protoc object_detection/protos/*.proto --python_out=.


...
若不成功【与protobuf版本有关】
执行以下
...


protoc object_detection/protos/anchor_generator.proto --python_out=.
protoc object_detection/protos/argmax_matcher.proto --python_out=.
protoc object_detection/protos/bipartite_matcher.proto --python_out=.
protoc object_detection/protos/box_coder.proto --python_out=.
protoc object_detection/protos/box_predictor.proto --python_out=.
protoc object_detection/protos/eval.proto --python_out=.
protoc object_detection/protos/faster_rcnn.proto --python_out=.
protoc object_detection/protos/faster_rcnn_box_coder.proto --python_out=.
protoc object_detection/protos/grid_anchor_generator.proto --python_out=.
protoc object_detection/protos/hyperparams.proto --python_out=.
protoc object_detection/protos/image_resizer.proto --python_out=.
protoc object_detection/protos/input_reader.proto --python_out=.
protoc object_detection/protos/keypoint_box_coder.proto --python_out=.
protoc object_detection/protos/losses.proto --python_out=.
protoc object_detection/protos/matcher.proto --python_out=.
protoc object_detection/protos/mean_stddev_box_coder.proto --python_out=.
protoc object_detection/protos/model.proto --python_out=.
protoc object_detection/protos/multiscale_anchor_generator.proto --python_out=.
protoc object_detection/protos/optimizer.proto --python_out=.
protoc object_detection/protos/pipeline.proto --python_out=.
protoc object_detection/protos/post_processing.proto --python_out=.
protoc object_detection/protos/preprocessor.proto --python_out=.
protoc object_detection/protos/region_similarity_calculator.proto --python_out=.
protoc object_detection/protos/square_box_coder.proto --python_out=.
protoc object_detection/protos/ssd.proto --python_out=.
protoc object_detection/protos/ssd_anchor_generator.proto --python_out=.
protoc object_detection/protos/string_int_label_map.proto --python_out=.
protoc object_detection/protos/train.proto --python_out=.
protoc object_detection/protos/graph_rewriter.proto --python_out=.
protoc object_detection/protos/flexible_grid_anchor_generator.proto --python_out=.
protoc object_detection/protos/calibration.proto --python_out=.

设置路径

# From tensorflow/models/research/
$ set PYTHONPATH= <Path to 'research' Directory> ; <Path to 'slim' Directory>
[例如]
set PYTHONPATH=D:\Anaconda\Lib\site-packages\tensorflow\models\research;D:\Anaconda\Lib\site-packages\tensorflow\models\research\slim

测试

# From tensorflow/models/
$ python object_detection/builders/model_builder_test.py

成功后

Ran 16 tests in 0.890s