Comments (4)
@MuhabHariri hi there,
Thank you for reaching out and providing details about the issue you're encountering with freezing layers in your custom YOLOv8 model. To assist you better, could you please provide a minimal reproducible code example? This will help us understand the context and reproduce the issue on our end. You can refer to our guide on creating a minimum reproducible example for more details.
Additionally, please ensure that you are using the latest versions of torch
and ultralytics
. You can upgrade your packages using the following commands:
pip install --upgrade torch ultralytics
Regarding your question, your interpretation is correct. In the YOLOv8 model, model.0
refers to the first layer, and model.19
would indeed correspond to the Detect layer if your YAML file is structured that way. The unexpected freezing of the model.19.dfl.conv.weight
layer could be due to a misconfiguration or an unintended side effect in the model's layer freezing logic.
Once you provide the reproducible example and confirm the versions, we can dive deeper into the issue and identify why the Detect layer's weight is being frozen.
Looking forward to your response!
from ultralytics.
@MuhabHariri DFL layers should always be frozen, this is all good.
from ultralytics.
@glenn-jocher Thank you for your response. Could you clarify further why DFL layers should always be frozen?
from ultralytics.
Hi @MuhabHariri,
Thank you for your follow-up question!
The DFL (Distribution Focal Loss) layers are designed to be frozen because they are part of the final detection head, which is responsible for refining the bounding box predictions. Freezing these layers helps maintain the stability of the model's output during training, ensuring that the learned distribution of bounding box coordinates remains consistent. This is particularly important for maintaining the accuracy and reliability of the model's predictions.
If you have any more questions or need further clarification, feel free to ask! 😊
from ultralytics.
Related Issues (20)
- Documenting the validation process in table HOT 2
- First call to yolov8 inference is slower than following inferences HOT 4
- Question on yolov8-pose HOT 1
- _plot_curve ValueError: object too small for desired array HOT 4
- Track ID Change HOT 1
- How to run tensorrt model on a specific device id, let's say device='1'. HOT 4
- Exporting to OpenVino does not work on Segmentation and classification when using CUDA HOT 2
- Missing a file when converting .pt model to RKNN model HOT 7
- YoloV8 Adding a new class without disturbing the trained classes HOT 2
- Can yolov8 simultaneously detect both bounding boxes and segments? HOT 1
- How to achieve real time (>= 25 fps) object detection in a video stream? HOT 1
- Using yolov10x.pt, predicting specific classes fails. HOT 2
- YOLOv8-Pose HOT 2
- YOLOV8 at 0.0 confidence? HOT 2
- Yolo OBB, poor orientation on squares but excellent on rectangles HOT 4
- YOLOv8-Seg HOT 2
- wandb shows unused labels after COCO transfer-learning HOT 1
- Issue with Training YOLOv8 on a Large Dataset with lack of memory and not good enough HOT 2
- Fail to run on videos from some specific cameras HOT 1
- ScannerError when import ultralytics HOT 2
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.