转换DeepLabV3+模型失败！！！

我也在嘗試轉換這個，同樣有問題，
請版主回覆一下

使用rknn-toolkit v1.3轉檔發生以下問題，是有甚麼不支持的操作嗎?

--> Build RKNN model...
W The RKNN Model generated can not run on simulator when pre_compile is True.
cc1: warning: command line option ‘-std=c++11’ is valid for C++/ObjC++ but not for C
cc1: warning: command line option ‘-std=c++11’ is valid for C++/ObjC++ but not for C
vnn_frozeninferencegraph.c: In function ‘vnn_CreateFrozenInferenceGraph’:
vnn_frozeninferencegraph.c:5142:31: error: ‘vsi_nn_resize_param {aka struct _vsi_nn_resize_param}’ has no member named ‘align_corners’
     node[249]->nn_param.resize.align_corners = True;
                               ^
vnn_frozeninferencegraph.c:5142:48: error: ‘True’ undeclared (first use in this function); did you mean ‘free’?
     node[249]->nn_param.resize.align_corners = True;
                                                ^~~~
                                                free
vnn_frozeninferencegraph.c:5142:48: note: each undeclared identifier is reported only once for each function it appears in
make: *** [vnn_frozeninferencegraph.o] Error 1
/bin/sh: 1: /tmp/tmp3rouo9uz/gen_nbg: not found
mv: cannot stat '/home/aver/rknn/rknn-toolkit/example/rknn_convert/*.nb': No such file or directory
mv: cannot stat '/home/aver/rknn/rknn-toolkit/example/rknn_convert/*.dat': No such file or directory
E Generate nbg failed.

按照你建議的，但是一直卡在rknn.init_runtime
python export_rknn_precompile_model.py non_precompile.rknn precompile.rknn
--> Export RKNN model
done
--> Init runtime environment
卡在這裡兩小時了還無法完成