whenet model converted from onnx to ncnn gives nan output.

xkftehaa  于 3个月前  发布在  其他
关注(0)|答案(1)|浏览(41)

error log | 日志或报错信息 | ログ

context | 编译/运行环境 | バックグラウンド

I am trying to convert WHEnet model to ncnn. Onnxruntime gives correct output but ncnn inference shows nan outputs.

how to reproduce | 复现步骤 | 再現方法

  1. onnx2ncnn onnx model.
  2. run ncnn inference on converted model and print outputs
    I have uploaded the onnx & ncnn models.
    whenettf_bs1.zip
xam8gpfp

xam8gpfp1#

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