Comments (3)
I met the same problem before. I think this may because the stride of your backbone network is different from the author's.
You can try resizing the labels, features and predictions to the same size to see if it works.
from contrastiveseg.
I met the problem, and It's because ur decoder have already upsample the predictions, like after the encoder maybe the feature_map's h w is 16X16 , so the embed is bsXembed_dimX16X16, but if your decoder upsample the feature_map maybe ur prediction is like 128X128, this would report an error.
the solution is resize your prediction to the same size as the embed like the way to do with labels
from contrastiveseg.
@tfzhou Does the proposed solution from @q671383789 answers the question? Thanks a lot for your great work!
from contrastiveseg.
Related Issues (20)
- 关于特征可视化的代码 HOT 1
- Extremely slow validation during training + cpu overload HOT 2
- The L2 normalization of features HOT 2
- T-SNE of features visualization HOT 1
- loss_contrast HOT 2
- maybe bug in ./segmentor/trainer_contrastive.py HOT 5
- how to reproduce the HRNet result trained on cityscapes trainval
- Momentum Update HOT 2
- How to reproduce the SoTA result of Cityscapes? HOT 1
- Semi-Hard Example Sampling implementation HOT 3
- code confusing me in def._sample_negative HOT 4
- Example for max_views, max_samples? HOT 2
- problem with resuming training from checkpoint
- loss_contrast与loss_contrast_mem两个版本中的PixelContrastLoss区别
- About the dimension of feature embedding HOT 1
- Code bug HOT 1
- @tfzhou So, the class 0 is the ignore index and not the background class? I mean, for the background class is applied also the contrastive loss. Right? HOT 4
- Dataloader distributed or not
- Running the t code shows loss=nan when calculating the coco dataset. HOT 4
- CKPT
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 contrastiveseg.