Comments (10)
from crowddet.
我想了一下,是否是我loss函数设置有问题,两个emd头应该是不能使用相同的gt的
from crowddet.
Maybe it is one of the reasons. In our paper, a proposal should predict 2 detections to cover 2 different targets. And our schema is mainly deployed to the two-stage detection frameworks. It will aggravate the problem of imbalance between positive and negative samples because an anchor infers at least 2 detections in the one-stage detection framework. Therefore, the performance could be better if the imbalance problem can be addressed. Besides, it does not work when the focal loss is included in the EMD loss.
from crowddet.
您好,请问一下,我把您的算法和思路移植到了yolo系列下,您的论文中对此的可行性也有提及,可是我在使用相同的crowdhuman数据集进行校验是出现了检测框重叠的问题,按照您的setNMS算法,检测框确实会出现重叠在同一目标的情况,请问您是怎么解决这一问题的,我在您的论文和开源的代码RetinaNet实现中没有发现相应的解决方案。
您好,能请问一下您是怎么将EMD移植到YOLO系列中的呢,求助!
from crowddet.
from crowddet.
你可以尝试直接使用focal loss而不是emd loss,这样就能够收敛了,也就是说模型在训练过程中暂时不用先考虑permutation invariance.
from crowddet.
from crowddet.
如果是做工程的话,可以尝试:https://arxiv.org/pdf/2012.03544.pdf.端到端的物体检测,做工程落地的话已经够了.
from crowddet.
所以想问下EMDloss不能用在one-stage目标检测算法中吗
from crowddet.
Maybe it is one of the reasons. In our paper, a proposal should predict 2 detections to cover 2 different targets. And our schema is mainly deployed to the two-stage detection frameworks. It will aggravate the problem of imbalance between positive and negative samples because an anchor infers at least 2 detections in the one-stage detection framework. Therefore, the performance could be better if the imbalance problem can be addressed. Besides, it does not work when the focal loss is included in the EMD loss.
所以想问下EMDloss不能用在one-stage目标检测算法中吗
from crowddet.
Related Issues (20)
- 怎么在COCO数据集上进行训练 HOT 1
- [Question] Integrating the model to be used with FastMOT
- where is "init_weights = '/data/model/resnet50_fbaug.pth'" HOT 2
- no config.py in repo HOT 1
- setnms有gpu版本吗? HOT 4
- Multilabel single bounding box HOT 1
- AttributeError in training
- EMDLoss:取min问题 HOT 8
- 复现该idea之后的奇怪情况 HOT 3
- onnx and tensorrt
- Is there a pytorch version of Cascade RCNN EMD?
- 关于模型来源的问题
- Set NMS HOT 1
- Could you please release code trained with coco dataset or how can I convert coco to odgt format? Thank you. HOT 1
- 测试模型
- 预训练模型网盘链接失效 HOT 1
- citypersons数据集的配置问题 HOT 4
- 用VOC数据集
- NCCL error when running train.py
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 crowddet.