davidhuangal
davidhuangal
Why in train_autodeeplab.py do you not run `self.architect.step (image_search, target_search)` until epoch > 19 ?
For my use case, I do not want any foreground images to overlap when being placed in a background image. Is there a way to prevent this from happening?
I have noticed that training is significantly slower with MMYOLO as opposed to Ultralytics using the same parameters and environment. I.e., using the same set of GPUs with the same...
When performing testing, the per-class metrics are displayed in a PrettyTable, but they are not saved to disk anywhere. Is there a setting for this or does this feature not...