使用1.5版本的rknn_model_zoo转onnx到rknn报错

[Newcomer-CL]

Traceback (most recent call last): File "../../../../../common/rknn_converter/rknn_convert.py", line 99, in convert(config_dict, args) File "../../../../../common/rknn_converter/rknn_convert.py", line 19, in convert rknn = cp.convert() File "/home/wjn/RKNN1808/rknn_model_zoo/common/rknn_converter/phase.py", line 122, in convert load_function(**model_config_dict['load']) File "/home/wjn/miniconda3/envs/rr/lib/python3.8/site-packages/rknn/api/rknn.py", line 150, in load_onnx ret = self.rknn_base.load_onnx(model, inputs, input_size_list, outputs) File "rknn/api/rknn_base.py", line 309, in rknn.api.rknn_base.RKNNBase.load_onnx File "/home/wjn/miniconda3/envs/rr/lib/python3.8/site-packages/rknn/base/acuitylib/init.py", line 1, in from acuitylib.optimize.optimizer import Optimizer File "rknn/base/acuitylib/optimize/optimizer.py", line 9, in init rknn.base.acuitylib.optimize.optimizer File "/home/wjn/miniconda3/envs/rr/lib/python3.8/site-packages/rknn/base/acuitylib/init.py", line 1, in from acuitylib.optimize.optimizer import Optimizer ImportError: cannot import name 'Optimizer' from partially initialized module 'acuitylib.optimize.optimizer' (most likely due to a circular import) (/home/wjn/miniconda3/envs/rr/lib/python3.8/site-packages/rknn/base/acuitylib/optimize/optimizer.cpython-38-x86_64-linux-gnu.so)

就是这个from acuitylib.optimize.optimizer import Optimizer 没有 Optimizer

[Newcomer-CL]

使用的转换脚本时1.5版本下的rknn_model_zoo/models/CV/object_detection/yolo/RKNN_model_convert/convert_yolo.sh

[kaisawind]

pip uninstall torch
pip install tensorflow==2.2.0
pip install torch==1.10.0