Comments (3)
Code for multi-task will be release in the future.
from yolov9.
Hi, I wanted to ask the same.
The segment folder already exists and the train.py script looks similar to the yolov7 version to me.
Will you provide the yolo-seg.pt weights? Or can I use the pretrained weights provided for yolov7?
When I am trying to train from scratch with the provided yolov7-af-seg.yaml cfg file I am facing the following issue:
Traceback (most recent call last):
File "segment/train.py", line 646, in
main(opt)
File "segment/train.py", line 542, in main
train(opt.hyp, opt, device, callbacks)
File "segment/train.py", line 220, in train
hyp['obj'] *= (imgsz / 640) ** 2 * 3 / nl # scale to image size and layers
KeyError: 'obj'
Edit:
By changing line 11: "dfl: 0.7" to "obj: 0.7" it seems to work now. Still some pretrained weights will be appreciated.
from yolov9.
Hi, I wanted to ask the same. The segment folder already exists and the train.py script looks similar to the yolov7 version to me. Will you provide the yolo-seg.pt weights? Or can I use the pretrained weights provided for yolov7? When I am trying to train from scratch with the provided yolov7-af-seg.yaml cfg file I am facing the following issue:
Traceback (most recent call last): File "segment/train.py", line 646, in main(opt) File "segment/train.py", line 542, in main train(opt.hyp, opt, device, callbacks) File "segment/train.py", line 220, in train hyp['obj'] *= (imgsz / 640) ** 2 * 3 / nl # scale to image size and layers KeyError: 'obj'
Edit: By changing line 11: "dfl: 0.7" to "obj: 0.7" it seems to work now. Still some pretrained weights will be appreciated.
Hi dear
I have similar error, can you guide me to solve it?
from yolov9.
Related Issues (20)
- How to use validation score in training yolov9 model HOT 1
- Training HOT 1
- SPPF,SPPELAN
- Meaning of `--local_rank` argument.
- Using multiple GPU inference time on yolov9
- Question about training images counter
- The trained YOLOv9-c model size is different from this repo reported
- Issue Integrating CBAM with YOLOv9 - Spatial Dimension Mismatch Error HOT 2
- How can I see feature visualization inside each block? HOT 1
- Using best.py model locally in VS Code
- Yolov9-s is slower than Yolov9-c. Why is this? HOT 2
- accelerted by tensorrt
- About class name HOT 1
- Request for Integration of Transformer and C3TR Modules into YOLOv9
- YoloV9-Tiny-Obb
- AttributeError: module 'cv2.dnn' has no attribute 'DictValue'
- ValueError: not enough values to unpack (expected 3, got 2)
- YOLOv9-T version # param discrepancy
- YOLOv9-t BFLOPs discrepancy HOT 3
- Question about 5.4.2 in paper and reversible branch
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 yolov9.