关于pytorch转化RKNN成功，初始化环境出错的问题

D:\Anaconda3\envs\rknn\python.exe "D:\PyCharm 2019.1.2\helpers\pydev\pydevd.py" --multiproc --qt-support=auto --client 127.0.0.1 --port 56080 --file G:/googleDownload/RKNN/RKNN/rknn-toolkit/examples/pytorch/resnet18/test.py
pydev debugger: process 12192 is connecting

Connected to pydev debugger (build 191.7141.48)
--> config model
done
--> Loading model
D:\Anaconda3\envs\rknn\lib\site-packages\onnx_tf\common\__init__.py:87: UserWarning: FrontendHandler.get_outputs_names is deprecated. It will be removed in future release.. Use node.outputs instead.
  warnings.warn(message)
./model.pt ********************
WARNING: Token 'COMMENT' defined, but not used
WARNING: There is 1 unused token
done
--> Building model
done
--> Export RKNN model
done
--> Init runtime environment
E RKNNAPI: rknn_init,  msg_load_ack fail, ack = 1(ACK_FAIL), expect 0(ACK_SUCC)!
E RKNNAPI: ==============================================
E RKNNAPI: RKNN VERSION:
E RKNNAPI:   API: 1.3.0 (c5654ea build: 2019-12-25 08:54:18)
E RKNNAPI:   DRV: 0.9.8 (943f8e8 build: 2019-07-03 17:51:17)
E RKNNAPI: ==============================================
E Catch exception when init runtime!
E Traceback (most recent call last):
E   File "rknn\api\rknn_base.py", line 988, in rknn.api.rknn_base.RKNNBase.init_runtime
E   File "rknn\api\rknn_runtime.py", line 320, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
E Exception: RKNN init failed. error code: RKNN_ERR_MODEL_INVALID
E Current device id is: TS018082190800713
E Devices connected:
E ['TS018082190800713']
Init runtime environment failed

进程已结束，退出代码 -1

上述环境：Win10，python3.6 torch1.2.0 rknn-toolkit 1.3.0 ，另外在RK1808计算棒上面就行相关计算。
出现上述错误，这是Bug，还是我模型问题？ 理论上，如果模型框架不支持的话，在转化为.rknn文件是会报错误，但是成功运行到初始化函数，这就想不通了。

你这里DRV和API版本不匹配是一定会出问题的，请把DRV版本也升级到1.3.x

PC端，怎么升级？

在RK3399Pro板子上面，DRV和API版本都是1.3.0版本，同样也出现了上述问题。

在台式上面这里的DRV是指计算棒的版本吗？Win10 只支持RK1808计算棒