RV1126上按教程部署 PP-LiteSeg 会提示 Malloc error

按照教程编译的 fastDeploy 和 PP-LiteSeg

然后到板子上运行会报错：

[3 4/20 17:35:11. 74 ...r/src/driver/verisilicon_timvx/engine.cc:193 Build] Build the tim-vx graph success.
D [_check_swapped_tensors:114]Check swapped tensors
[3 4/20 17:35:11.104 ...r/src/driver/verisilicon_timvx/engine.cc:260 Execute] Process cost 13721 us
[3 4/20 17:35:11.108 ...le-Lite/lite/kernels/nnadapter/engine.cc:248 Execute] Process cost 33372 us
[F 4/20 17:35:11.113 ...ite/lite/backends/host/target_wrapper.cc:33 Malloc] Check failed: p: Error occurred in TargetWrapper::Malloc period: no enough for mallocing 159383552 bytes.
terminate called after throwing an instance of 'paddle::lite::PaddleLiteException'
what(): Paddle-Lite C++ Exception:
[F 4/20 17:35:11.113 ...ite/lite/backends/host/target_wrapper.cc:33 Malloc] Check failed: p: Error occurred in TargetWrapper::Malloc period: no enough for mallocing 159383552 bytes.

前面的 log 过长，都是模型信息就补贴上来了。

同时我试了按照教程部署 PaddleClas 和 yolov5 都没有问题。

报错原因是资源不够，但是这不是官方例程么？板子也没有运行其他程序怎么会资源不够呢，可以的话请大佬们指教一下

Start with the RV1126 build-and-install guide and the PP-LiteSeg example at examples/vision/segmentation/paddleseg/semantic_segmentation/rockchip/rv1126/cpp, then reproduce the deployment on the board. Compare it with the working PaddleClas and yolov5 deployments while examining the reported 159383552-byte Malloc failure. Done means identifying the cause and documenting or correcting the example so the official deployment runs successfully.