Fatal signal 11 (SIGSEGV),

Qengineering / Face-Recognition-Jetson-Nano

Recognize 2000+ faces on your Jetson Nano with database auto-fill and anti-spoofing

https://qengineering.eu/deep-learning-examples-on-raspberry-32-64-os.html

BSD 3-Clause "New" or "Revised" License

108 stars 31 forks source link

Fatal signal 11 (SIGSEGV), #7

Closed kikirizki closed 3 years ago

kikirizki commented 3 years ago

Hi thanks for your amazing work, I tried to run arcface on android, but it I keep getting Fatal signal 11 (SIGSEGV). If I change the output Blob name from fc1 to output the error does not show up but it return empty tensor

Qengineering commented 3 years ago

Sorry @kikirizki, I'm afraid I can't be of any help on this. I haven't written or testes the software on android. Both, MNN and ncnn can run on android, something you surely knew.

kikirizki commented 3 years ago

Hi @Qengineering , Thank you for your prompt response, would you mind point me out about how did you convert the weight from the original arcface to.paramand .bin file. I will try to convert it myself, thank you.

Qengineering commented 3 years ago

A part of the project I've copied from GitHub as listed in the Thanks. Here the model was already converted. On his turn Xinghao has used this GitHub repo. There is a conversation about training

kikirizki commented 3 years ago

@Qengineering Thank you for help, I will close this issue