Is there a way different than Pandas to read bounding box data?

[RRighart]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

I am using Yolov5 for training and torch.hub.load for loading the trained model.
Using Pandas, I am able to get a nice table with boundary box information.

results = model(img, size=640)
df = results.pandas().xyxy[0]

As Pandas can become memory intense, I was wondering if there is a different way of loading the same data, using for example Numpy. I would be very grateful for any useful reference on this topic!

Additional

No response

[glenn-jocher]

@RRighart see PyTorch Hub Tutorial for readout options.

YOLOv5 Tutorials

• Train Custom Data  🚀 RECOMMENDED
• Tips for Best Training Results  ☘️ RECOMMENDED
• Weights & Biases Logging  🌟 NEW
• Roboflow for Datasets, Labeling, and Active Learning  🌟 NEW
• Multi-GPU Training
• PyTorch Hub  ⭐ NEW
• TFLite, ONNX, CoreML, TensorRT Export 🚀
• Test-Time Augmentation (TTA)
• Model Ensembling
• Model Pruning/Sparsity
• Hyperparameter Evolution
• Transfer Learning with Frozen Layers  ⭐ NEW
• Architecture Summary  ⭐ NEW

Good luck 🍀 and let us know if you have any other questions!

[RRighart]

Thank you ! I have seen the PyTorch Hub Tutorial.
Actually I realise that the Numpy solution depends on counting and selecting the right columns manually, which can be dangerous if other columns are inserted at some point. For ex. if I need confidence scores, I need to put 4:

arr = results.xyxy[0].cpu().numpy()
arr[:,4]  

You also present the json method. I was wondering, is there a way to avoid using pandas in the middle?

d = results.pandas().xyxy[0].to_json(orient='records')

[glenn-jocher]

@RRighart the standard outputs are tensors. You're free to do anything you want with them.

[github-actions]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov5/wiki
• Tutorials – https://docs.ultralytics.com/yolov5
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com/hub
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!