Comments (6)
Every pixel in the image will be assigned a label, even if it does not fit the true category. Box is even one of the categories the model was trained on.
from esanet.
@mona0809 Thank you for your reply. Ok I will test it.
from esanet.
Even if each pixel is assigned to one of the known classes, the network might still be able to detect unknown objects with some height on the ground. During tests in real-world applications, we observed that the floor class is detected quite robustly and might help to find objects on the ground (see our video).
I am not sure whether this helps you. However, if your example above is your application scenario, give it a try.
from esanet.
@danielS91 Thank you.
I checked the NYUV2 dataset and there is 'void' in the classes. If there is unseen object detected, is it classified as 'void' ?
from esanet.
Void is ignored during training. You could try to train with void but there is no guarantee that every unkown object will be classified as void. As void is very versatile it is hard to learn a representation.
from esanet.
@mona0809 I see. Maybe I should train the model with additional dataset and see the result.
I appreciate.
from esanet.
Related Issues (20)
- the issue about confusion matrix HOT 1
- How can I change resnet18 to mobilenetv2? HOT 2
- logs.csv doesn't exist HOT 3
- onnx inference problem HOT 2
- Make ESANet work with arbitrary input size/shape HOT 2
- Where to find Dataset Inference results HOT 1
- A question about the unit of depth value(m or mm) HOT 2
- Train my own dataset without void class HOT 2
- It uses the NYU pre-training model to verify the semantic segmentation effect on the Replica dataset HOT 1
- What is the difference between PPM and APPM? HOT 2
- load_weight problem HOT 2
- Can I use ESANet with a Realsense-camera in real time with pre-trained models?
- How to pre-process depth when the train and test data are taken from different distance? HOT 3
- cityscapes weights not working
- third dimension issue with our images when using Cityscapes weight HOT 8
- Pretrained weight for Cityscapes (RGB-only) HOT 2
- About confusion_matrix.py HOT 1
- NYUV2 weight test SUNRGBD HOT 3
- Where can I see model learning & inference result data image?
- Training Time and Result Viewing Method
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 esanet.