ncnn Unsupported Ops?

u4vypkhs  于 4个月前  发布在  其他
关注(0)|答案(1)|浏览(57)

error log | 日志或报错信息 | ログ

model | 模型 | モデル

tinypose256.onnx.zip

  1. original model

how to reproduce | 复现步骤 | 再現方法

1.python3 -m onnxsim tinypose256.onnx tinypose256-sim.onnx
2.onnx2ncnn tinypose256-sim.onnx tinypose256.param tinypose256.bin

I got errors while convert the onnx model into ncnn model,
it shows this:

Shape not supported yet!
Unknown data type 0
Unsupported Resize scales and sizes are all empty!
Shape not supported yet!
Unknown data type 0
Unsupported Resize scales and sizes are all empty!
Shape not supported yet!
Unknown data type 0
Unsupported Resize scales and sizes are all empty!
ArgMax not supported yet!
  # axis=-1
  # keepdims=0

Please help, thanks a lot!

8xiog9wr

8xiog9wr1#

针对onnx模型转换的各种问题,推荐使用最新的pnnx工具转换到ncnn
In view of various problems in onnx model conversion, it is recommended to use the latest pnnx tool to convert your model to ncnn

pip install pnnx
pnnx model.onnx inputshape=[1,3,224,224]

详细参考文档
Detailed reference documentation
https://github.com/pnnx/pnnx
https://github.com/Tencent/ncnn/wiki/use-ncnn-with-pytorch-or-onnx#how-to-use-pnnx

相关问题