Comments (1)
Hello! It looks like you're facing some challenges with the OBB detection performance on your custom dataset. Here are a couple of suggestions that might help improve the results:
-
Data Augmentation: Even though you've mentioned it, ensuring a diverse range of rotations and scales in your augmentations can be crucial for OBB tasks.
-
Hyperparameter Tuning: Adjusting learning rate, batch size, or using different optimizers might yield better results.
-
Increase Dataset Size: If possible, increasing the dataset size or adding more varied examples for underperforming classes could help.
-
Advanced Techniques: Consider using techniques like transfer learning from a similar task or integrating attention mechanisms that might help the model focus better on oriented objects.
-
Post-Processing: Sometimes adjusting the confidence thresholds and NMS parameters during inference can significantly change the outcomes.
If these adjustments don't lead to improvements, it might be helpful to review the annotations for accuracy or experiment with different architectures. Keep us posted on your progress! 🚀
from ultralytics.
Related Issues (20)
- Bug heatmap ultralytics 8.1.34 HOT 4
- How do I get the coordinates of detected objects in yolov8 in real time and print? HOT 6
- Seeking Guidance on Integrating SuperPoint with YOLOv8 for Improved Keypoint and Object Detection HOT 2
- show_labels=False, show_conf=False parameters won't work (ultralytics==8.2.25) HOT 4
- Custom callback function HOT 8
- How to display OKS scores HOT 4
- Using OBB for pick and place on a robotic arm HOT 3
- Object Counting HOT 3
- Results of the same images different when used in validation or prediction HOT 5
- custom model architecture plot HOT 2
- Custom model in YOLOv8 HOT 5
- Custom Model Can Not Detection Object When Converted CoreML HOT 8
- Discrepancy in confusion matrix and Prediction.jon HOT 2
- Preprocessing bottleneck in YOLOv8 Classification HOT 19
- MacOS error with TFLite model inference end2end model HOT 1
- Segmentation for RTDERT HOT 3
- Change evaluation period HOT 4
- How does the confusion matrix of the object detection module works? HOT 4
- Difference between C2f and C2 HOT 5
- anchors of yolov8 HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ultralytics.