模型部署在rv1266报错

1.环境：
Linux debian10.toybrick 4.19.172 #130 SMP PREEMPT Wed Jun 16 19:25:46 CST 2021 armv7l GNU/Linux
2.版本信息
rknn-toolkit-lite 1.7.1.dev.090192be3b
3.报错信息


4.求助:
有啥解决办法或者建议吗

报错信息呢？仿真正确么？

报错信息
512, 512, 3)
--> Init runtime environment
librknn_runtime version 1.7.0 (0bef7b3 build: 2021-08-18 19:55:01 base: 1131)
E [op_check:185]Inputs/Outputs data type not support:  INT16,  INT32
E [setup_node:456]Check node[782] CAST fail
Create rknn graph fail!
Create RKNN model fail, error=-6
E Catch exception when init runtime!
E Traceback (most recent call last):
  File "/usr/local/lib/python3.7/dist-packages/rknnlite/api/rknn_lite.py", line 157, in init_runtime
    self.rknn_runtime.build_graph(self.rknn_data, self.load_model_in_npu)
  File "rknnlite/api/rknn_runtime.py", line 733, in rknnlite.api.rknn_runtime.RKNNRuntime.build_graph
Exception: RKNN init failed. error code: RKNN_ERR_MODEL_INVALID

Init runtime environment failed

仿真是用onnx去其他环境试一下吗?