Giorgio Segalla
Giorgio Segalla
You have to add the -na parameter to avoid the use of the image
I have same problem, have you solve in some way? I launch `pytest --cov= test.py` python version is 3.7
This would be amazing
This will be useful!
Same here, as you solved in some way?
> someone send to me a this solution Just avoid using Ninja and build NNPACK using cmake and make install. this solution is working but we had some problem of...
After I get an error when try to build the darknet-nnpack I create a new [issue](https://github.com/digitalbrain79/darknet-nnpack/issues/63#issue-827579417) try to check it got solved before test the comment above
> I didn't see this issue by my rasp pi 3B after the solved cmake issue and we gave up use darknet-nnpack when I send the email to digitalbrain79 he...
I don't understand why the time to get train on the model with all frozen layers, it's more than the backbone frozen layer. It would not be the inverse??