Digital2Slave

> Yes, coco 80 classes. You do not need change it for custom dataset. For the custom dataset, I use **yolov7** to train the object detect model. What I need...

@joeyballentine Four months have passed, do u find the solution ?

> > @joeyballentine Four months have passed, do u find the solution ? > > Yes, the solution is we are rewriting the entirety of onnx2ncnn in python. It's still...

> > > > @joeyballentine Four months have passed, do u find the solution ? > > > > > > > > > Yes, the solution is we are...

>  自问自答,解决了,见上图 @superbayes 你是用Python调用的么？

> > >  自问自答,解决了,见上图 > > > > > > @superbayes 你是用Python调用的么？ > > c++调用 嗯嗯，我准备用Python接口，目前没有现成的。我参考[yolov5.py](https://github.com/Tencent/ncnn/blob/master/python/ncnn/model_zoo/yolov5.py)自己修改了一个针对YoloV5l的。#4097

For **yolov5-v6.1** ``` # convert .pt to .onnx python3 export.py --weights path/to/your/*.pt --include onnx --train # convert .onnx to *-sim.onnx pip3 install onnx-simplifier python3 -m onnxsim path/to/your/*.onnx path/to/your/*-sim.onnx # out-of-the-box...

``` No LSB modules are available. Distributor ID: Ubuntu Description: Ubuntu 18.04.6 LTS Release: 18.04 Codename: bionic ``` - First install `pybind11` - Second install `ncnn` ``` $ pip install...

https://packages.deepin.com/deepin/pool/non-free/d/

Same problem on Mac book pro OS X.