Glenn Jocher comments

Results 1398 comments of


Glenn Jocher

Where is the Dataloader for OBB data

@dk-teknologisk-mlnn hello! Thanks for reaching out with your question. 🌟 The handling of Oriented Bounding Boxes (OBB) in YOLOv8 can indeed look a bit complex at first glance because of...

Where is the Dataloader for OBB data

@dk-teknologisk-mlnn hey there! Thanks for diving deep into the details and sharing your findings. 🕵️ Regarding the resampling of points to 100 for Oriented Bounding Boxes (OBB), it was intended...

Where is the Dataloader for OBB data

@dk-teknologisk-mlnn-mlnn That's fantastic to hear! 🎉 It sounds like the adjustments you've made, particularly with the resample = 5 and modifications to the augmentation strategy, are paying off. It's great...

warning: plotting error for ......exp\resulte.csv : \'value'must be an instance of str or bytes,not a float

@zhangsanliisi hey there! Thank you for reaching out and for your interest in contributing a PR! 😊 It sounds like you encountered a plotting error related to the type of...

Cropped Image size mismatches the bounding box Width and Height in the text file

@hareem-nisar thank you for bringing this to our attention! 🙏 It seems like the discrepancy between the dimensions of the cropped image saved by YOLOv8 and the bounding box dimensions...

Cropped Image size mismatches the bounding box Width and Height in the text file

Hi @hareem-nisar, Thanks for sharing the detailed output! It looks like the discrepancy might be related to how the bounding box coordinates are being converted and used for cropping. The...

Classification result using pre-trained model doesn't really make a lot of sense

We need to do some cleanup here. Saving should only occur on save=True, but I see this is the default as the same arg controls checkpoint saving during training

Classification result using pre-trained model doesn't really make a lot of sense

@SkalskiP YOLOv5 hub models handle this with Detections objects that then have many methods like results.show(), results.print() etc. we’d like to do something similar here but just haven’t had time....