Comments (5)
I have the same confusion !
Before the Bottleneck
, 2 convolution layers with stride 2 make the input down sample 4x. Should I up sample 4x after the final layer to recover the input size or change the stride of the first two convolution layer into 1 ?
from hrnet-semantic-segmentation.
I guess you might wanna check out other issues, the similar questions have been asked for a few times. But, my question is, put the bilinear upsampling layer before the final layer or after? cuz I believe if the final output comes from a bilinear upsampling layer, the output has to be a bit coarse.
from hrnet-semantic-segmentation.
Based on the author's reply here, it seems to be bilinear interpolation upsampling after the output
#15 (comment)
from hrnet-semantic-segmentation.
Thanks for your reply. I've seen the issue. But it seems to be a little coarse to bilinear 4x to predict directly. I want to know whether you have some solutions to address it?
from hrnet-semantic-segmentation.
If anyone else is wondering, how to train the model if the model output size is not equal to label size, check out this
from hrnet-semantic-segmentation.
Related Issues (20)
- Problem abput inplace_abn setup HOT 1
- About GFLOPs
- Training my own data(6 classes) as cityscapes-format, but got eval [0. 0.00423967 0.35140248 0. 0. 0. ]
- Why doesn't just use the gtmask for soft_object_regions
- The performance of cityscapes on Pytorch 1.8.1 HOT 3
- Is there a version of HRNet called HRNetv2-W28? HOT 1
- Loss for background class
- RGB images for pertained model vs BGR images for Semantic segmentation HOT 1
- about visualization
- Bug report/ Help watnted:
- where did you difined the variable "border_padding "?
- How to segment only selected classes (out of 19 in CityScapes) by using pretrained model?
- What does mean "base_size" HOT 1
- Can you provide a onnx model for me?
- Replacing BatchNorm with LayerNorm
- What is the model structure of small HRNet? HOT 1
- What is the reason for the fluctuation in the results after using random seeds
- some confusing problems in testval and validate
- Why weren't LIP and ADE20K evaluated as test sets?
- Unable to achieve the result on the README...
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 hrnet-semantic-segmentation.