DP1701

Problems with obj_loss

7

Hello all, I've done three trainings now and each one is bad because an overfitting is visible at obj_loss. The first one I did from scratch (orange), the second one...

Hi all, has anyone tried this method for outdoor applications? I will install a camera soon and the goal is to track several objects that are more than 50m away...

Scale images with percentages

3

Hey, is it possible to scale images and labels with percentages instead of entering a specific resolution? I have images in different resolutions and would like to scale them down...

Split a Dataset into n folds with the transform split function

7

Hello everyone, I am looking for a way to split a data set into n folds, taking into account the class distribution. The documentation says that this is possible with...

Cannot select specific coda device

2

### Search before asking - [X] I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and [discussions](https://github.com/ultralytics/yolov5/discussions) and found no similar questions. ### Question Hello everyone, unfortunately I cannot select a specific CUDA...

Problems with Jedi in VS Code

10

Hi, when I switch to Jedi in VS Code, built in modules are recognised correctly but other modules (for example PyTorch) installed with pip are not. Details can already be...

Influence of the augment paramter

3

### Search before asking - [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and found no similar questions. ### Question Hello, In the file args.yaml, after training with the...