Giorgio Segalla

Results 10 comments of 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 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??