Comments (3)
Some questions:
- Did you try diff input resolution than 640, i.e. lower 416?
- How big (# samples) is your training data?
- Which model are you using, is it pre-trained with COCO (weights provided by repo)?
Also, double check that mixup augmentation is not ruining your training. Try seeing if augmentation is what you expect. Below is a script I use to visualize the augmentation:
from yolov9.
@ankandrew hello
- i am using a bigger size 1024 for training my model, because the original document image is all high resolution
- I have 44000 training data, i think it is enough to train the model
- I am using yolov9-e and load the pretrained weights with coco
I check my augmentation, you are right, i didnt close the mixup augmentation. I check the augmentation using your scipts, than i close mosaic and copy_paste, i will train one more time with current setting.
by the way, i reading the code about compute loss. the bbox loss mainly focous on iou, I have doubt with the iou loss is not helpful for accurate bbox regression. So i change the loss to l1 loss, but I got a worse result, do you have any idea?
from yolov9.
Hi @travisCxy! Sorry for late response. I think your analysis on point (3) seems accurate. Seems existing MDPIoU
loss could be used instead of currently one used CIoU
. The MDPIoU
includes a penalty term based on the distance between the corners of the bounding boxes, which should make it more suitable for text detection where corner alignment is critical to avoid cropping letters (like in your examples). Let me know if this helps in your dataset.
Lines 292 to 296 in 5b1ea9a
You can use my branch to select the bounding box loss function or cherry pick my commit to easily test other loss functions than default one ankandrew@9527269.
from yolov9.
Related Issues (20)
- The GPU memory usage seems to be unstable. When setting the batch size to 16 for the smallest model, the GPU memory usage exceeds 24GB.
- Hello, I would like to ask if there is any difference between SPPF and SPPFELAN?
- turning off the AMP in yolov9/train.py
- SSL Certificate Verification Error During YOLOv9 Training HOT 1
- 进行训练时不运行 HOT 1
- Auto anchor seem not run when custom data have long box HOT 2
- COnvert custom yolov9 model trained into tflite format
- pt to onnx and How to use onnx model HOT 1
- yolov9 for custom model on macos just sucks?!!!! HOT 1
- AttributeError: 'DualDDetect' object has no attribute 'nm' HOT 1
- YOLOv9 DDP training with COCO
- Generating or Plotting a 'result.png' from 'result.csv' HOT 1
- Running custom model detection on GPU fails
- Muti GPU DDP issue : Expected to have finished reduction in the prior iteration before starting a new one. HOT 7
- train.py best.pt
- 4 Channel Live Inferencing
- Inconsistent anchor_t Value in YOLO Training Logs
- I get slightly different results from running val.py on my test dataset and running it myself in python with model.predict.
- How does yolov9 set detection targets to only one category HOT 1
- ’IndexError: list index out of range’ when running val.py with yolov9-c-converted.pt HOT 1
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.