Comments (1)
Thanks for your interest in our work.
-
Architecture in Figure 4 of the paper is generic. First skip connection between encoder and decoder makes sense if C is different than number of classes in the dataset. For cityscapes, number of classes is close to 19 so it does not make sense to add it. We experimentally found that this connection is irrelevant for the Cityscapes dataset.
-
Usually, semantic segmentation architectures use a pretrained encoder such as ResNet which is trained on the ImageNet. We did not use a pretrained encoder, that is why we need to adhere to two stage strategy. Also, we found that training end-to-end models from scratch are less accurate than 2 stage accuracy.
-
You could upsample the feature map and compute the loss at original image resolution instead of 1/8th of the image.
-
In general, ignoring the background is not a good idea, especially when considering the generalizability. I would like to emphasize that the aim of ESPNet is to build a network that is efficient with reasonable accuracy.
from espnet.
Related Issues (20)
- CUDNN_STATUS_INTERNAL_ERROR when training decoder on Cityscapes HOT 3
- optimizer.zero_grad() HOT 1
- ESPnet V2 accuracy HOT 2
- Train dataset with more than 20 classes HOT 2
- cuda runtime error(59) HOT 2
- double scale in test code HOT 4
- Size mismatch issue while testing retrained ESPNet on Cityscapes HOT 1
- About Performance Metric HOT 1
- Opencv Dnn HOT 1
- How do I train the segmentation categories I need ? HOT 1
- what value can you achieve about the result of cityscapes val ? HOT 1
- Exact versions of all the packages HOT 1
- Question about different torch sizes of decoding
- Comparison of ENet and ERFNet Model
- Regarding the assertion error- Assertion `t >= 0 && t < n_classes` failed
- How can I deploy the model on jeston AGX xavier?
- index 0 is out of bounds for dimension 0 with size 0
- Inverse class probability weights
- The segmentation mask overlayed on the image is gray not colored
- Pretrained models don't have a state dictionary 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 espnet.