Linzaer / Ultra-Light-Fast-Generic-Face-Detector-1MB

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)
MIT License
7.19k stars 1.54k forks source link

onnx2ncnn error #202

Open mathpopo opened 4 years ago

mathpopo commented 4 years ago

operation below ,but Segmentation fault (core dumped)

https://github.com/daquexian/onnx-simplifier

python3 -m onnxsim version-RFB-320_without_postprocessing.onnx version-RFB-320_simplified.onnx

Next, you can convert this onnx model like version-RFB-320_simplified.onnx into a ncnn model. Here is a website for online conversion : https://convertmodel.com/?tdsourcetag=s_pctim_aiomsg. You can also use the NCNN compiled conversion tool onnx2ncnn. Screenshot from 2020-06-04 11-29-59

mathpopo commented 4 years ago

(base) chenxin@Nitro-AN515:~/Downloads/Ultra-Light-Fast-Generic-Face-Detector-1MB/ncnn/build$ ./main /home/chenxin/Downloads/Ultra-Light-Fast-Generic-Face-Detector-1MB/models/onnx-test/version-slim-320_simplified.bin /home/chenxin/Downloads/Ultra-Light-Fast-Generic-Face-Detector-1MB/models/onnx-test/version-slim-320_simplified.param /home/chenxin/Downloads/Ultra-Light-Fast-Generic-Face-Detector-1MB/imgs/3.jpg Processing /home/chenxin/Downloads/Ultra-Light-Fast-Generic-Face-Detector-1MB/imgs/3.jpg Segmentation fault (core dumped)

mathpopo commented 4 years ago

Screenshot from 2020-06-04 11-56-40 ra-Light-Fast-Generic-Face-Detector-1MB$ python -m onnxsim /home/chenxin/Downloads/Ultra-Light-Fast-Generic-Face-Detector-1MB/models/onnx/version-slim-320.onnx /home/chenxin/Downloads/Ultra-Light-Fast-Generic-Face-Detector-1MB/models/onnx-test/version-slim-320_simplified.onnx Simplifying... Checking 0/3... Checking 1/3... Checking 2/3... Ok! compare exist version-slim-320_simplified.onnx and onnxsim result

just use exist version-slim-320_simplified.onnx --> ncnn bin param ,it work well

Screenshot from 2020-06-04 11-56-40