ONNX模型转换RKNN模型失败(亟待解决)

[复制链接] · 发表于 2021-9-6 18:20:56

onnx模型为Pytorch转换而来，使用的ONNX版本为1.6,不知道是不是因为版本太高的原因导致转换失败

*************************
all device(s) with ntb mode:
TS018083201100794
*************************
devices: ([], ['TS018083201100794'])
--> config model
done
--> Loading model
WARNING: ONNX Optimizer has been moved to https://github.com/onnx/optimizer.
All further enhancements and fixes to optimizers will be done in this new repo.
The optimizer code in onnx/onnx repo will be removed in 1.9 release.

W Call onnx.optimizer.optimize fail, skip optimize
W Unknown batch size of input input, set it to 1 to do shape inference, may cause errors.
E Calc node Conv : Conv_0 output shape fail
W ----------------Warning(2)----------------
E Catch exception when loading onnx model: ./ParseHandwritingDecimalScore.onnx!
E Traceback (most recent call last):
E File "rknn/base/RKNNlib/onnx_ir/onnx_numpy_backend/shape_inference.py", line 65, in rknn.base.RKNNlib.onnx_ir.onnx_numpy_backend.shape_inference.infer_shape
E File "rknn/base/RKNNlib/onnx_ir/onnx_numpy_backend/ops/conv.py", line 49, in rknn.base.RKNNlib.onnx_ir.onnx_numpy_backend.ops.conv.Conv
E File "/home/septnet/.local/lib/python3.7/site-packages/torch/__init__.py", line 19, in <module>
E exit(-1)
E File "/home/xlg/mambaforge/envs/py37_septnet/lib/python3.7/_sitebuiltins.py", line 26, in __call__
E raise SystemExit(code)
E SystemExit: -1
E During handling of the above exception, another exception occurred:
E Traceback (most recent call last):
E File "rknn/api/rknn_base.py", line 292, in rknn.api.rknn_base.RKNNBase.load_onnx
E File "rknn/base/RKNNlib/RK_nn.py", line 141, in rknn.base.RKNNlib.RK_nn.RKnn.load_onnx
E File "rknn/base/RKNNlib/app/importer/import_onnx.py", line 118, in rknn.base.RKNNlib.app.importer.import_onnx.Importonnx.run
E File "rknn/base/RKNNlib/converter/convert_onnx.py", line 94, in rknn.base.RKNNlib.converter.convert_onnx.convert_onnx.__init__
E File "rknn/base/RKNNlib/converter/convert_onnx.py", line 984, in rknn.base.RKNNlib.converter.convert_onnx.convert_onnx._shape_inference
E File "rknn/base/RKNNlib/onnx_ir/onnx_numpy_backend/shape_inference.py", line 70, in rknn.base.RKNNlib.onnx_ir.onnx_numpy_backend.shape_inference.infer_shape
E File "rknn/api/rknn_log.py", line 312, in rknn.api.rknn_log.RKNNLog.e
E ValueError: Calc node Conv : Conv_0 output shape fail
Load mobilenet_v1 failed!

只看该作者 · 发表于 2021-9-7 18:04:59

计算棒相关版本
NPU:version 6.4.3.5.293908
rknn-server:1.6.0
librknn_runtime version 1.6.0

Python相关版本
Python:3.7.10

Package             Version       Location
-------------------- --------------- -------------------------------
absl-py             0.13.0
astor             0.8.1
backcall          0.2.0
cached-property    1.5.2
cachetools          4.2.2
certifi             2021.5.30
chardet             3.0.4
click             8.0.1
Cython             0.29.24
decorator          5.0.9
dill                0.2.8.2
Flask             1.0.2
flatbuffers       1.10
future             0.18.2
gast                0.2.2
google-auth       1.35.0
google-auth-oauthlib 0.4.6
google-pasta       0.2.0
grpcio             1.39.0
h5py                2.8.0
idna                2.8
importlib-metadata 4.8.1
ipython             7.27.0
itsdangerous       2.0.1
jedi                0.18.0
Jinja2             3.0.1
joblib             1.0.1
Keras-Applications 1.0.8
Keras-Preprocessing  1.1.2
lmdb                0.93
Markdown          3.3.4
MarkupSafe          2.0.1
matplotlib-inline 0.1.2
networkx          1.11
numpy             1.21.2
oauthlib          3.1.1
onnx                1.8.1
onnx-tf             1.2.1
onnxruntime       1.8.1
opencv-python       4.5.3.56
opt-einsum          3.3.0
p5py                1.0.0
parso             0.8.2
pep517             0.11.0
pexpect             4.8.0
pickleshare       0.7.5
Pillow             5.3.0
pip                21.2.4
ply                3.11
prompt-toolkit    3.0.20
protobuf          3.17.3
psutil             5.6.2
ptyprocess          0.7.0
pyasn1             0.4.8
pyasn1-modules    0.2.8
pybind11          2.7.1
Pygments          2.10.0
PyYAML             5.4.1
requests          2.22.0
requests-oauthlib 1.3.0
rknn-toolkit       1.7.0
rsa                4.7.2
ruamel.yaml       0.15.81
scikit-learn       1.0.dev0       /home/septnet/rknn/scikit-learn
scipy             1.5.4
setuptools          57.5.0
six                1.16.0
tensorboard       2.0.2
tensorflow          2.0.0
tensorflow-estimator 2.0.1
termcolor          1.1.0
threadpoolctl       2.2.0
tomli             1.2.1
torch             1.6.0a0+b31f58d
traitlets          5.1.0
typing             3.7.4.3
typing-extensions 3.10.0.2
urllib3             1.25.11
wcwidth             0.2.5
Werkzeug          2.0.1
wget                3.2
wheel             0.37.0
wrapt             1.12.1
zipp                3.5.0

只看该作者 · 发表于 2022-1-7 11:05:36

提示：E ValueError: Calc node Conv : Conv_0 output shape fail，卷基层0的输出形状失败，是不是在config的时候指定了input的shape和实际的模型对不上？

只看该作者 · 发表于 2022-4-26 10:08:23

最新版本1.7.1试一下