pt导出onnx并推理ok，但是onnx转rknn过程build报错_M_range_check

[复制链接] · 发表于 2023-9-22 17:47:55

本帖最后由 htzhao 于 2023-9-22 17:49 编辑

D RKNN: [17:35:15.277] >>>>>> start: N4rknn20RKNNMultiSurfacePassE

D RKNN: [17:35:15.277] <<<<<<<< end: N4rknn20RKNNMultiSurfacePassE

D RKNN: [17:35:15.277] >>>>>> start: N4rknn14RKNNTilingPassE

E build: Catch exception when building RKNN model!

E build: Traceback (most recent call last):

E build:   File "rknn/api/rknn_base.py", line 2012, in rknn.api.rknn_base.RKNNBase.build

E build:   File "rknn/api/rknn_base.py", line 384, in rknn.api.rknn_base.RKNNBase._generate_rknn

E build:   File "rknn/api/rknn_base.py", line 348, in rknn.api.rknn_base.RKNNBase._build_rknn

E build: IndexError: vector::_M_range_check: __n (which is 2) >= this->size() (which is 3)
复制代码

看了下日志，不知是否和这个有关

I 

I Output[1140] shape with str value may cause error, replace ['Mul1140_dim_0', 'Mul1140_dim_1', 'Mul1140_dim_2', 'Mul1140_dim_3'] with [1, 1, 720, 1280].

I Output[1142] shape with str value may cause error, replace ['Mul1142_dim_0', 'Mul1142_dim_1', 'Mul1142_dim_2', 'Mul1142_dim_3'] with [1, 1, 180, 320].

I correct_ops ...

I correct_ops done.
复制代码