Михаил
@RangiLyu Maybe you’re here and the project hasn’t been abandoned yet?
> @MiXaiLL76 Thank you for your support Thanks for a good framework!
@hhaAndroid Hi! Can you update your status?
@hhaAndroid @ZwwWayne Is anyone else working on the project? Maybe we can take it on as support?
The project is dead.
> compute_metrics - 465 - The testing results of the whole dataset is empty. This is normal, it means that your model did not predict a single bbox!) > learning...
> @MiXaiLL76 i read in the previous issues [ #2942 ] it stated that the learning rate reduce by 10x will resolve the issues but it didnt. and Im also...
> @MiXaiLL76 I have emailed you. Did you received it? Hello! Yes, I received a message, I'll see today when I'm free from work
[pipeline.zip](https://github.com/user-attachments/files/15956708/pipeline.zip) Here is an example of my result using your data.  ```bash +----------+-------+--------+--------+-------+-------+-------+ | category | mAP | mAP_50 | mAP_75 | mAP_s | mAP_m | mAP_l | +----------+-------+--------+--------+-------+-------+-------+...
> What was the issue in my config file that cause only half of the Train set to go missing? You setup ```py train_dataloader = dict( batch_sampler=dict(type='AspectRatioBatchSampler'), batch_size=2, ``` total...