Comments (6)
谢谢你的关注。可以通过CAM得到person的seed,可能loss需要换成sigmoid+cross entropy loss。
from dsrg.
@speedinghzl 你好,请问训练生成种子的程序是这个吗?https://github.com/ascust/SEC-MXNet
我现在想在自己的数据集上做训练生成只有人的种子,但是我只有少量的图片,大概只有1000多张,这样的话,训练生成的种子会不会不准确?
from dsrg.
1000+图训练分类器是可以的(只有最后一层参数是随机初始化的)。
另外1000+图片都是有人的吗?如果是可能数据集并不适合训练CAM来定位人的位置。
from dsrg.
@speedinghzl 你好,我现在有大概1000张不到的在同一场景连续拍摄的有人的图片,然后我用了一些方法把这1000张图片里的人给去掉了,并利用背景修复技术,把人身后的背景又复原到图片上,请问我用这大概2000张的图片来训练CAM,能得到定位人的位置的种子吗?
from dsrg.
如果可以把人去掉,意味着可以生成pixel-level label,就没必要使用弱监督分割了。直接使用pixel-level label训练一个人的segmentation network会比弱监督分割的结果要好。
from dsrg.
@speedinghzl 你好,我是想用已有的语义分割模型,但是这些语义分割模型并没有在我的数据集场景下做过训练,因此并不能很完美的分割出人的部分,也就是说属于人的pixel-level label并不是足够准确的。而且,我的数据集都是含有人的,所以我想把这些图片上的人利用现有的语义分割模型分割出来,然后为了训练CAM,利用背景修复技术,把人身后的背景又复原到图片上,生成种子,最后将原始的语义分割模型作为预训练模型,并使用您的DSRG方法来再次训练,请问使用这样的方法训练出来的模型在我的数据集上的分割效果能比原始模型好吗?谢谢!
from dsrg.
Related Issues (20)
- Do you add val split data for training when report results on test split HOT 2
- Comprehension of pretrained VGG16 model HOT 3
- questions about seed-loss
- About Loss Function HOT 1
- A juvenil question
- Training with custom data
- Failed to load caffe layers
- Loss calculation is too slow HOT 2
- Understanding Seeding Loss
- Understanding the data in `localization-cues.pickle` file HOT 3
- I can't run 'pip install CRF/'.
- Question about seed dynamic updating HOT 4
- about vgg16_20M_mc.caffemodel
- Localization cues HOT 3
- How to generate localization-cues.pickle file using personal dataset, voc style? HOT 1
- what image size has been used for the final segmentation training?
- resnet weights initialized from ImageNet? HOT 2
- Reproducing Paper Results HOT 7
- comprehension of DSRG 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 dsrg.