Comments (3)
@Wenlong0913 hello! It's great to see your dedication to preparing your dataset for training with YOLOv5. 🚀
When it comes to dataset preparation, having all relevant objects labeled in your images is crucial for achieving high model performance. In your case, since humans appear in some of your images but are not labeled, this could potentially lead to the model learning to ignore humans or, worse, misclassifying them. This is especially important since you mentioned humans are one of your target classes.
While it might seem like a daunting task to go through your images to ensure all instances of your classes (human, cat, dog) are labeled, it's a necessary step for the kind of accuracy and reliability you're likely aiming for. Unlabeled instances of target classes can introduce noise into your training data, leading to poorer model performance.
Adding background images without your target classes can indeed help reduce false positives, but it doesn't substitute the need for accurately labeled data across your classes of interest. If manual labeling for every instance is too labor-intensive, you might consider semi-automated labeling tools or services to assist in the process, ensuring that every relevant object in your dataset is properly marked.
Remember, the quality of your training data directly impacts the effectiveness of your trained model. Taking the time to ensure it's as accurate and comprehensive as possible will pay off in your model's performance. 🌟
If you have any more questions or need further assistance, feel free to ask. Happy training!
from yolov5.
Thanks, man.
from yolov5.
@Wenlong0913 you're welcome! If you have any more questions down the road or need further assistance, don't hesitate to reach out. Happy training and best of luck with your project! 🚀
from yolov5.
Related Issues (20)
- Similar mAP when splitting data into train, val and test HOT 4
- Syntax and understanding questions about reading tensorflow lite results HOT 1
- A Error which blast my mind.... HOT 1
- Yolov5 Int8 export in PyTorch HOT 10
- Video inference with YOLOv5 model in python HOT 3
- How to disable or add new scales of prediction? HOT 5
- Installation on Windows 7 32 bits HOT 3
- Artificial Neural Network - interpreting model.save output HOT 1
- Origin of warmup_bias_lr? HOT 3
- Silicon Mac GPU Support for training HOT 1
- Split features map of data HOT 1
- incorrect detections for cars after fine-tuning yolov5l HOT 1
- tried to run yolov5 "detect.py" with pretrained model yolov8x.pt and xView.yaml HOT 1
- Low disk space causes memory leak HOT 3
- Error with fbgemm.dll file when using Torch! HOT 5
- Yolov5 inventing label on validation set HOT 1
- challenges faced in Xtream1 tool while creating class ID's HOT 1
- Facing issues while changing class ID values HOT 1
- background color of image and other causes? HOT 1
- ModuleNotFoundError: No module named 'models.yolo'. HOT 3
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 yolov5.