Comments (11)
I didn't remove the negative images from the output of image split algorithms. For center+wh+theta, I used the same training skills and architectures except for the output branches for a fair comparison.
from bbavectors-oriented-object-detection.
I also wonder how to adopt CenterNet by adding an extra angle prediction branch, could you mention the code of this part?
Thanks @ yijingru @Tarazed
from bbavectors-oriented-object-detection.
Change heads
in the main.py
:
heads = {'hm': num_classes[args.dataset],
'wh': 2,
'reg': 2,
'angle': 1
}
and change the ground-truth accordingly (wh
is the width and height of the box, angle \in [-90,0)
is theta
in Fig1a, note ground-truth theta
is already calculated in datasets/base.py
. I used SmoothL1
loss for angle regression.
from bbavectors-oriented-object-detection.
Change
heads
in themain.py
:heads = {'hm': num_classes[args.dataset], 'wh': 2, 'reg': 2, 'angle': 1 }
and change the ground-truth accordingly (
wh
is the width and height of the box,angle \in [-90,0)
istheta
in Fig1a, note ground-truththeta
is already calculated indatasets/base.py
. I usedSmoothL1
loss for angle regression.
I have found a strange phenomenon: when I used the 3rd channel of 'wh' head to predict angle, I got 0.636 of mAP, but when I used an extra branch to predict angle as you said, I got 0.530 mAP... I set the random seed to 0, the performance of which is a little bit lower than random seed. I'm confused as extra branch should be better.
from bbavectors-oriented-object-detection.
Maybe training loss matters. I used weighted loss asloss = hm_loss + wh_loss + off_loss + 0.1*angle_loss
. The multi-tasks are hard to optimize sometimes. But we do see the angle is hard to learn for the network.
from bbavectors-oriented-object-detection.
Maybe training loss matters. I used weighted loss as
loss = hm_loss + wh_loss + off_loss + 0.1*angle_loss
. The multi-tasks are hard to optimize sometimes. But we do see the angle is hard to learn for the network.
That's awesome! The loss weight of multi-task can significantly affect the results! After changing the weight of angle_loss, I got 0.68mAP! Thank you very much!
from bbavectors-oriented-object-detection.
Maybe training loss matters. I used weighted loss as
loss = hm_loss + wh_loss + off_loss + 0.1*angle_loss
. The multi-tasks are hard to optimize sometimes. But we do see the angle is hard to learn for the network.That's awesome! The loss weight of multi-task can significantly affect the results! After changed the weight of angle_loss, I got 0.68mAP! Thank you very much!
My pleasure.
from bbavectors-oriented-object-detection.
i also want to know the loss weight of multi-task of 0.68mAP, can you share it? thanks very much! @Tarazed
from bbavectors-oriented-object-detection.
i also want to know the loss weight of multi-task of 0.68mAP, can you share it? thanks very much! @Tarazed
just the same as what the author replied, loss = hm_loss + wh_loss + off_loss + 0.1*angle_loss
from bbavectors-oriented-object-detection.
@Tarazed 请问用原始的centernet加一个额外的角度,除了main.py,还需要修改哪里嘛
from bbavectors-oriented-object-detection.
@Tarazed 请问用原始的centernet加一个额外的角度,除了main.py,还需要修改哪里嘛
Change the ground-truth accordingly in base.py
from bbavectors-oriented-object-detection.
Related Issues (20)
- 关于HRSC数据集的最好结果 HOT 2
- TypeError: 'int' object is not iterable HOT 2
- IndexError: list index out of range in Eval phase when file names have different format
- 测试和评估阶段问题 HOT 1
- 怎么生成trainval.txt和test.txt? HOT 1
- how to train my custom dataset is in coco json format? HOT 2
- ModuleNotFoundError: No module named 'dota_kit' HOT 3
- down ratio and coordination order HOT 1
- ModuleNotFoundError: No module named 'dota_kit' HOT 1
- Question about wrong implementation in decode_prediction()
- KeyError: 'container-crane' HOT 5
- dota的map只有63 HOT 2
- when turn resnet101 to resnet18 and resnet34 in ctrbox_net.py(line13), got problem!! HOT 2
- 可以展示一下数据集的结构嘛,也就是datasets的目录结构
- dota上loss多少可以认为已经收敛? HOT 1
- 对比试验 HOT 1
- 环境搭建
- 测试fps
- Inquiry Regarding Download of the Dataset Used in the Paper [Object-Guided Instance Segmentation With Auxiliary Feature Refinement for Biological Images]
- 请问7×7卷积在哪里 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 bbavectors-oriented-object-detection.