Comments (9)
Only one refinement module is trained. It is then used in the global/local step. They are not trained separately.
from cascadepsp.
Thanks a lot, I get it. If I train the network on very high resolution images, could you please tell me what do I need to do to modified the onlinetransformdataset? Do I still need to use random crop 224x224?
from cascadepsp.
I haven't tried that but I suspect that you would need something more complicated.
At least you would need to use RandomResizedCrop
instead of RandomCrop
to get global context sometimes. That might lead to an overwhelming amount of useless crops (all foreground/background) and they should be discarded.
Moreover, when you do have high-res training data, one suggestion is to actually train the two steps separately -- one using downsampled large crops for the global step, and the other using small crops for the local step. This is not implemented in the current repo but might worth a try.
from cascadepsp.
I see. I notice that the test dataset named "BIG_PSPNet_SS" you provided is large enough. Could I know how did you train the two steps on this dataset?
from cascadepsp.
We did not train the model on this dataset. It is too small and is for testing purposes only.
from cascadepsp.
So, if I want to train on this dataset. I need to firstly generate the input data for global step. And use the output of global step to continuely generate input data for local step. Is that right?
from cascadepsp.
That's one way.
Another way is to generate the inputs for the global/local steps separately and independently by perturbing the ground-truth.
from cascadepsp.
May I ask whether using the groundtruth-based perturbation results as "seg" or using the network-based prediction results as "seg" is better for training the two step? Have you compared these two situations?
from cascadepsp.
For our case (training two steps as a single module), it is better to use perturbation because we can generate much more training pairs with variations. I would suspect that it will also be better to use ground-truth perturbation even when you train them separately.
from cascadepsp.
Related Issues (20)
- Runtime Error: - Invalid Load Key, '<'. HOT 2
- Error while running demo code!! HOT 4
- How to change epoch? HOT 3
- Segmentation Refinement Runtime Error HOT 11
- Train the Net HOT 4
- How to implement 'Local step' only? HOT 2
- how to solve this problem? HOT 2
- refinement is not a binary image HOT 1
- Can this method be used as post-processing for video object segmentation? HOT 2
- local step only HOT 4
- Help with Colab/local setup HOT 3
- Tree leaves boundary refinement HOT 5
- hashlib error HOT 1
- weight coefficient
- Very slow prediction, high cpu /gpu usage HOT 1
- Car Window Refinement
- Whether this model can be applied to Cityscapes datasets? HOT 1
- How to train PSPNet/DeepLabV3+ just as the result in your paper HOT 12
- Any low hanging fruit for generation speed improvements? HOT 2
- About the problem of dealing with redundant incomplete masks 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 cascadepsp.