011基于Anaconda实现tensorflow目标检测环境搭建

傷城~ 2023-07-06 08:54 2阅读 0赞

1、下载models：链接:https://pan.baidu.com/s/1TNeg20BvkgxruqyTH\_ClxA 密码:rky0  
2、下载cocoapi：[https://github.com/cocodataset/cocoapi.git][https_github.com_cocodataset_cocoapi.git]

git clone https://github.com/cocodataset/cocoapi.git

3、参考官方提供的文档配置环境  
[https://github.com/tensorflow/models/blob/master/research/object\_detection/g3doc/installation.md][https_github.com_tensorflow_models_blob_master_research_object_detection_g3doc_installation.md]  
我是的环境是Anaconda下的，专门创建了学习tensorflow的环境，基于python3.  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2F5YW5nYW5uOTE1_size_16_color_FFFFFF_t_70]

搭建环境要注意是在哪个版本下搭建，之前就是弄错了结果一直不能导包，到最后一步检查时提示没有contrib，这是因为默认的base环境下我没有install tensorflow。

4、在anaconda下配置子环境时，所有的文件都在envs文件夹下，将models文件夹放在envs下的tensorflow文件夹中，因为这里我将子环境命名为tensorflow

(base) appledeMacBook-Pro:~ apple$ activate tensorflow
    (base) appledeMacBook-Pro:~ apple$ conda info -e
    # conda environments:
    #
    base                  *  /anaconda3
    tensorflow               /anaconda3/envs/tensorflow

可以看出默认是base环境，所以将models文件夹放在…/anaconda3/envs/tensorflow/下，同时将下载好的cocoapi放在models里。

5、接下来是cocoapi的安装  
官方步骤是：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2F5YW5nYW5uOTE1_size_16_color_FFFFFF_t_70 1]

进入cocoapi中的PythonAPI文件夹，对里面Makefile执行make操作：  
因为我是在tensorflow子环境中，所以在终端要切换环境：

(base) appledeMacBook-Pro:~ apple$ conda activate tensorflow

make操作：

(tensorflow) appledeMacBook-Pro:~ apple$ cd /anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/models/cocoapi/PythonAPI 
    (tensorflow) appledeMacBook-Pro:PythonAPI apple$ make

makefile文件：

all:
        # install pycocotools locally
    	python3 setup.py build_ext --inplace
    	rm -rf build
    
    install:
    	# install pycocotools to the Python site-packages
    	python3 setup.py build_ext install
    	rm -rf build

要注意的是文件里面使用的是python，要改成python3

make编译之后生成了pycocotools文件夹，将这个文件夹复制到models/research/中

6、接下来步骤protoc，research文件夹下的objec\_detection下的protos里面的文件都执行了且生成相应的.py文件  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2F5YW5nYW5uOTE1_size_16_color_FFFFFF_t_70 2]  
添加依赖：因为要使用slim  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2F5YW5nYW5uOTE1_size_16_color_FFFFFF_t_70 3]  
最后运行目标检测里面的文件看是否成功：

python object_detection/builders/model_builder_test.py

直接复制粘贴到终端：  
即：

(tensorflow) appledeMacBook-Pro:research apple$ protoc object_detection/protos/*.proto --python_out=.
    (tensorflow) appledeMacBook-Pro:research apple$ export PYTHONPATH=$PYTHONPATH:`pwd`:`pwd`/slim
    (tensorflow) appledeMacBook-Pro:research apple$ python3 object_detection/builders/model_builder_test.py
    ..............
    ----------------------------------------------------------------------
    Ran 14 tests in 0.080s

可以看出执行成功即配置正确。

[https_github.com_cocodataset_cocoapi.git]: https://github.com/cocodataset/cocoapi.git
[https_github.com_tensorflow_models_blob_master_research_object_detection_g3doc_installation.md]: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2F5YW5nYW5uOTE1_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20200217141946195.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2F5YW5nYW5uOTE1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2F5YW5nYW5uOTE1_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/202002171428199.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2F5YW5nYW5uOTE1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2F5YW5nYW5uOTE1_size_16_color_FFFFFF_t_70 2]: https://img-blog.csdnimg.cn/20200217144525706.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2F5YW5nYW5uOTE1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2F5YW5nYW5uOTE1_size_16_color_FFFFFF_t_70 3]: https://img-blog.csdnimg.cn/20200217144957777.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2F5YW5nYW5uOTE1,size_16,color_FFFFFF,t_70