Closed MannyGozzi closed 2 years ago
@MannyGozzi you appear not to understand LR schedulers. There is no point in comparing epoch 6/6 with epoch 6/50, they should not be similar at all.
@MannyGozzi you appear not to understand LR schedulers. There is no point in comparing epoch 6/6 with epoch 6/50, they should not be similar at all.
I'll run the comparison again with the same epoch count, my apologies for not knowing.
@MannyGozzi you appear not to understand LR schedulers. There is no point in comparing epoch 6/6 with epoch 6/50, they should not be similar at all.
Alright results have been recalculated using the same command, only a change to 7 epochs instead of the previous 50. The output is shown below and remains consistent with my question. Why are the metrics so comparatively low when using the custom anchor values that are output from the most optimal run?
@MannyGozzi evolve doesn't output anchors, evolve outputs a set of hyperparameters that are evolved on your scenario. If autoanchor was used during evolution then likewise it should be used during training.
I was hoping to have the same anchor values across runs. I altered the autoanchor.py file to see if the weights are being brought in from the model.yaml file and it seems they aren't. See the attached image.
@MannyGozzi as AutoAnchor says if you want to use these for a future run then just put them in your model.yaml file and then point to it during training, i.e. --cfg model.yaml
@MannyGozzi as AutoAnchor says if you want to use these for a future run then just put them in your model.yaml file and then point to it during training, i.e. --cfg model.yaml
These are the anchors in the model file that I'm pointing to:
@MannyGozzi if you're using default hyps everything should be fine, i.e. https://github.com/ultralytics/yolov5/blob/b367860196a2590a5f44c9b18401dedfc0543077/data/hyps/hyp.scratch-low.yaml#L20
@MannyGozzi if you're using default hyps everything should be fine, i.e.
I understand but the fact that it doesn't seem to use the anchors in the model cfg file is concerning. Is that a bug?
There is no bug. Everything works correctly. If I change yolov5s.yaml first anchor to 1,1 and point to it the updated anchors are displayed in the console and used for training:
Search before asking
Question
Above is the best run from evolving hyperparameters using the --evolve flag with a very short number of epochs and evolutions just to demonstrate a point. The code used to run this example was:
The outputted anchor values were placed inside the model.yaml file I was using
I ran a normal, non-evolution run using these optimal hyperparameters:
And found the following results. Using this command:
Is there any reason why these anchor values are outputting such horrible metrics in comparison to when they were used in the evolution runs?
Additional
No response