Comments (1)
@tsing90 Hi, could you please share how you get this output? I download the Adobe dataset too, and I still don't know why the fg image are not original image, which all have some shadow on the outside of body.
And another question is did you test the model on your own images. I tried to segment the object with instance segmentation and add trimap to the mask, then use THE author's pretrained model, not so good in my case, maybe I didn't operate right.
Here is my result of your test, outsied boader ....
from pytorch-deep-image-matting.
Related Issues (20)
- the evaluation code HOT 1
- License HOT 2
- How to calculate connectivity error HOT 2
- size mismatch for conv6_1.weight: copying a param with shape torch.Size([512, 512, 1, 1]) HOT 2
- Is the training stable enough to always converge to the numbers in README.md HOT 2
- CUDA out of memory HOT 3
- About learning rate setting HOT 9
- pytorch-deep-image-matting implementation on Android HOT 2
- performance for stage2 HOT 7
- Automatic Background Removal technology HOT 8
- Getting horrible performance, why?
- composition.py
- step parameter
- Can I run this without CUDA?
- The new pretrained model released on 9th Sep caused corrupt when load HOT 3
- question regarding alpha being used in generating trimap
- what's the meaning of training stage 0,1,2,3?
- I got ahorrible performance HOT 1
- 运行demo.py收到了一个报错 HOT 1
- How to generate trimap without alpha matte?
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 pytorch-deep-image-matting.