Comments (12)
Hi @kelisiya,
Sorry for the late reply due to the CVPR deadline.
Do you mean the training loss? or calculating the evaluation errors?
The connectivity loss is not used in training, it is only used when evaluating the matte quality. It should be fine if following my instructions to run the code.
from indexnet_matting.
Hi @kelisiya,
Sorry for the late reply due to the CVPR deadline.
Do you mean the training loss? or calculating the evaluation errors?
The connectivity loss is not used in training, it is only used when evaluating the matte quality. It should be fine if following my instructions to run the code.
It's work , I let your backbone to DIM and use Alpha loss and Grad loss , finally I can train your model .
from indexnet_matting.
@kelisiya Nice, let me know if your model achieves better results:)
from indexnet_matting.
from indexnet_matting.
@kelisiya It is normal that the network's output is not bounded by [0, 1] due to the nature of regression. This is why postprocessing is required to eliminate unreasonale outputs.
However, you should not use the clip operator or clamp in pytorch during training, because the gradient will be clipped to zero either. This may be the reason why the loss does not decrease.
The clip operator should be only applicable in inference.
from indexnet_matting.
from indexnet_matting.
I don't use cv.normalize.
I also tried sigmoid, but do not find it necessary.
from indexnet_matting.
from indexnet_matting.
Exactly!
from indexnet_matting.
from indexnet_matting.
from indexnet_matting.
Of course you should normalize the alpha before calculating the loss.
Yes, the concatenated input like DIM.
from indexnet_matting.
Related Issues (20)
- Automatic Background Removal technology HOT 1
- License question HOT 3
- Reproducing results HOT 22
- Correct the relative path and switch to the CPU. HOT 1
- errors when use model.train() HOT 2
- How to solve this error? When I run this net to predict an image,I have GPU,But I want not to use it. HOT 2
- Questions about B11 model HOT 2
- Train Own Dataset HOT 3
- train on multi gpu HOT 2
- RandomCrop 对于图像尺寸320的处理会抛出异常 HOT 2
- Is the validate in training necessary? HOT 2
- error in loading pre-trained model to train on multi-gpu HOT 3
- Adobe Image Matting dataset HOT 1
- Possible reasons for different performance between DIM Re-implementation and original implementation HOT 1
- Training on custom data set
- In terms of speed of reasoning, whether you can achieve real time
- Where can I download the dataset? HOT 3
- freeze_bn seems to be an invalid option HOT 3
- How can I train the DIM?
- Rare inconsistency for background image size during data loading 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 indexnet_matting.