Smonkey123
Smonkey123
Thank you for your great YOLO models (v5, v8, 11). I have met the same question, and I tried many times to retrain, but the same error will generate, before...
Sorry to interrupt you again, I disabled the Windows Defender, this question continue exists. I found the weights (last.pt) wrote into this folder successfully (runs\\detect\\train\\exp7\\weights\\) when every time this error...
@Y-T-G During the training process, I continuously monitor the weights folder. The weight file (last.pt) keeps updating (the “Date modified” attribute changes as the training proceeds), but at a certain...
I found similar questions (#7087, #7509), and the real reason might be that Windows Defender is occupying/scanning last.pt. Unfortunately, my PC belongs to my company, and the firewall is controlled...
@Y-T-G Maybe you are right, thank you very much. I modify 'batch=48', each epoch consume about 20s, now, every goes well. 
Note that when deploying a local LLM using ollama, your local LLM needs to be parameterized to support JSON output, so that it can be parsed by the JSON parser...
What you said is indeed correct. To add an additional parameter, we can set whether to allow the original LLM response to be displayed first in the middle. This might...