【RKNN Toolkit 1.6.0】在PC端的Ubuntu16.04中安装RKNN Toolkit 1.6.0开发环境

1. 背景目标

利用RK3399pro平台，移植深度学习目标检测算法，实现嵌入式平台的深度学习应用
本文在PC端的Ubuntu16.04中安装RKNN Toolkit 1.6.0开发环境，方便模型转换（例如从tensorflow平台下的.pb文件转换为RK平台下需要的.rknn文件）

2. 实操步骤

2.1 利用conda创建新的环境

conda create -n [name] #创建名为name的conda环境，如tensorflow
source activate [name]     #激活刚才创建的环境，命令完成后，回答先命令行之前多了刚创建的环境的名字

2.2 依赖包和环境要求：

2.3 安装RKNN1.6.0和相关依赖包

（1）离线whl包均从rockcip官方源下载，链接如下：http://repo.rock-chips.com/pypi/simple/

• 离线包名称：rknn_toolkit-1.6.0-cp36-cp36m-linux_x86_64.whl

（2）将下载的离线包利用pip进行安装，因为利用conda install无法安装

• 使用pip将对应的包安装在指定的conda环境的指定的python目录下；
• 注意：如果直接使用pip install，会存在问题，将会同时安装在多个不同环境的python下；
• 执行该pip时候，需要在rknn_toolkit-1.6.0-cp36-cp36m-linux_x86_64.whl文件所在目录下：

python3.6 -m pip install -t 相关目录/anaconda3/envs/rknn_1.6/lib/python3.6/site-packages/ rknn_toolkit-1.6.0-cp36-cp36m-linux_x86_64.whl

执行该指令后，就会同时下载必要的依赖包。

2.4 运行官方提供的demo，测试RKNN是否安装成功

从官方github仓下载 rknn-toolkit-v1.6.0-packages：
https://github.com/rockchip-linux/rknn-toolkit

python3 test.py
--> Config model
done
--> Loading model
W The target_platform is not set in config, using default target platform rk1808.
W:tensorflow:From /home/user/venv/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py:1814: py_func (from tensorflow.python.ops.script_ops) is deprecated and will be removed in a future version.
Instructions for updating:
tf.py_func is deprecated in TF V2. Instead, there are two
    options available in V2.
    - tf.py_function takes a python function which manipulates tf eager
    tensors instead of numpy arrays. It's easy to convert a tf eager tensor to
    an ndarray (just call tensor.numpy()) but having access to eager tensors
    means `tf.py_function`s can use accelerators such as GPUs as well as
    being differentiable using a gradient tape.
    - tf.numpy_function maintains the semantics of the deprecated tf.py_func
    (it is not differentiable, and manipulates numpy arrays). It drops the
    stateful argument making all functions stateful.
    
done
--> Export RKNN model
done
--> Init runtime environment
done
--> Running model
done
--> Evaluate model performance
W When performing performance evaluation, inputs can be set to None to use fake inputs.
========================================================================
                               Performance                              
========================================================================
Layer ID    Name                                         Time(us)
57          openvx.tensor_transpose_3                    125
117         convolution.relu.pooling.layer2_2            204
115         convolution.relu.pooling.layer2_2            404
112         convolution.relu.pooling.layer2_2            416
110         convolution.relu.pooling.layer2_2            597
107         convolution.relu.pooling.layer2_2            245
105         convolution.relu.pooling.layer2_2            503
...         ...                                          ...
23          fullyconnected.relu.layer_3                  13
29          fullyconnected.relu.layer_3                  8
Total Time(us): 10218
FPS(600MHz): 73.40
FPS(800MHz): 97.87
Note: Time of each layer is converted according to 800MHz!
========================================================================

done

3. 其他相关博客

【RKNN-Toolkit-Tensorflow】得到不同模型的box_priors.txt文件（如：rknn-toolkit\example\mobilenet-ssd中）