rknn-toolkit
rknn-toolkit copied to clipboard
rockchip-linux
E [op_optimize:428]CONCAT, uid 85 must have same quantize parameter! E [op_optimize:428]CONCAT, uid 85 must have same quantize parameter!
使用文档中，量化过程支持 "由深度学习框架 导出 量化模型， RKNN Toolkit 加载 并利用已有的 量化 信息 ,生成量化 RKNN模型。支持的深度学习框架（括号内为主要支持版本，请尽量使用对应版本生成的量化模 型）： PyToch(v1.9.0)、 ONNX(Onnxruntime v1.5.1)、 Tensorflow、 TFLite。" 使用文档显示可以导入带有量化信息的模型，但在导入带有FakeQuantize的onnx模型时，导入失败。
同样的模型，input channel==1转换失败，input channel==3转换成功。失败信息： D:\Users\xxxxx\Miniconda3\envs\rknn_v1.75\lib\site-packages\numpy\_distributor_init.py:32: UserWarning: loaded more than 1 DLL from .libs: D:\Users\xxxxx\Miniconda3\envs\rknn_v1.75\lib\site-packages\numpy\.libs\libopenblas.TXA6YQSD3GCQQC22GEQ54J2UDCXDXHWN.gfortran-win_amd64.dll D:\Users\xxxxx\Miniconda3\envs\rknn_v1.75\lib\site-packages\numpy\.libs\libopenblas.WCDJNK7YVMPZQ2ME2ZZHJJRJ3JIKNDB7.gfortran-win_amd64.dll stacklevel=1) W rknn-toolkit version: 1.7.5 W Detect torchvision(0.11.0). If the python program got segment fault error,...
pytorch：1.10.0 rknn_toolkit: 1.7.5 转换环境：官方1.7.5的docker 错误： E Catch exception when loading pytorch model: ./ocr_ht_waferlabel/resnet18v1_ocr_det_qat_script_best.pt! E Traceback (most recent call last): E File "rknn/base/RKNNlib/app/importer/import_pytorch.py", line 131, in rknn.base.RKNNlib.app.importer.import_pytorch.ImportPytorch.run E File "rknn/base/RKNNlib/converter/convert_pytorch_new.py", line...
当前NPU模型输出状态： ``` input tensors: index=0 name=x.1_0 n_dims=4 dims=[1 3 640 640] n_elems=1228800 size=1228800 fmt=0 type=3 qnt_type=2 fl=0 zp=0 scale=1.000000 output tensors: index=0 name=permute_at_1747_221_out0_223 n_dims=5 dims=[3 80 80 11] n_elems=211200 size=211200...
For rknn-toolkit2 here is info on dynamic shape support - [page 88, Section 5.4.3 Generate RKNN Model of Dynamic Shape](https://github.com/rockchip-linux/rknn-toolkit2/blob/b25dadacc24b88eb7dfcaa47c9c525ecca89b319/doc/02_Rockchip_RKNPU_User_Guide_RKNN_SDK_V1.6.0_EN.pdf) Just want to know if rknn-toolkit supports dynamic shape too...
--> Config model done --> Loading model E Catch exception when loading pytorch model: best.onnx! E Traceback (most recent call last): E File "rknn\base\RKNNlib\converter\convert_pytorch_new.py", line 3967, in rknn.base.RKNNlib.converter.convert_pytorch_new.convert_pytorch.load E File...
W rknn-toolkit version: 1.7.5 W Verbose file path is invalid, debug info will not dump to file. D Using CPPUTILS: True --> config model done --> Loading model I Start...
