Brendan Horsfield
Brendan Horsfield
@Klimroth, @shadeofplato, @zohaibjan: Did anyone ever figure out a solution to this problem? I am having pretty much the exact same problem that @Klimroth originally reported. In my case, I...
@Klimroth, I have created a custom callback that will enable you to load a checkpoint that was created during training. I also fixed a bug in the `load_model()` method in...
@zohaibjan, did you ever find a solution to this problem?
@zohaibjan, thanks for the tip, I've never heard of the TAO Toolkit before. It looks like an excellent platform, especially for less experienced ML developers. I will definitely check it...
For anyone who is still trying to use the YOLOv4 model in this GitHub repo, I have some progress to report: In order to load a saved model after custom...
I have created a custom callback that will enable you to save a checkpoint during training in a format that can be loaded back in from file later using the...
Understood, thanks for letting me know.
> It seems to me that you appreciate working with archives over loose files, just like me. Yes, this is usually my preference, especially in cases where the end user...
@Deschain, thanks for the suggestion. I have tried this on my target platform and achieved good results. During the archiving process I can see that my internal storage remains unchanged,...