Comments (9)
Q#1, we report the results on 60 classes, while EncNet achieves 51.7 mIoU on 59 classes w/o background.
Q#2, we didn't try the latter one.
from danet.
Question 1:
For Q#1, the paper achieves 52.6 in mIoU without using DA, Multi-Grid or MS ?
Question 2:
For the two attention modules, do you try to empoly sigmoid op to obtain weight rather than softmax ?
from danet.
Q#1, Yes
Q#2, We don't try sigmoid, in fact, we think softmax is more appropriate since it involves all pixels
from danet.
Question 1:
args.lr = lrs[args.dataset.lower()] / 8 * args.batch_size in option.py means that the lr is relate to batch_size you give. Is that the lr not fixed depending on the batch_size (GPU memory)?
from danet.
Question 1:
I am sorry for bothering you again. What are the base size and crop size of PContext dataset for training and multi-scale test?
from danet.
On the PContext dataset, the base size is set to 608 and crop size is set to 576. Multi-scale test is adopted, you can refer to the experimental settings of PyTorch-Encoding
from danet.
@qiulesun @junfu1115 Hi, I have mailed the authors of CCL(i.e., [6] in DANet). The result of [6] in Table 6 is actually 59 classes without background and with single scale testing. It may be unfair to compare with CCL directly :(
from danet.
@junfu1115 trivial questions and suggestions #179 and Performance on Pascal Context #78 give different strategies to compute mIoU on 60 classes for PASCAL Context. They confused me deeply. How does DANet calculate the mIoU on 60 classes ?
from danet.
@junfu1115
Q1: In DANet, could you provide the settings of base size and crop size for each dataset ?
Q2: CAM_Module computes the energy_new before softmax while PAM_Module not, why ?
Q3: Your repo mainly follows Pytorch-Encoding. I note that there are two different ways to compute mIoU on 60 classes for PASCAL Context (see issues from trivial questions and suggestions #179 and Performance on Pascal Context #78). How does DANet calculate the mIoU on 60 classes ?
from danet.
Related Issues (20)
- How to visualize the attention map? HOT 1
- No module named 'encoding'?how to solve it? HOT 7
- In DANet, questions of features channels HOT 1
- 关于pascal_voc
- 训练时网络参数报错怎么解决? HOT 11
- Connection Error when downloading Pascal Dataset HOT 3
- pre-training weight HOT 1
- When i try to train or test danet i get this error HOT 1
- TypeError: cross_entropy_loss(): argument 'input' (position 1) must be Tensor, not tuple HOT 1
- DRAN model in MMsegmentation? HOT 1
- Failed downloading url HOT 1
- requests.exceptions.ConnectionError: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))
- ValueError: operands could not be broadcast together with shapes (1,1024,2048) (1024,2048,4)
- AttributeError: 'tuple' object has no attribute 'log_softmax'` HOT 2
- from option import Options
- 训练DANet
- python setup.py install
- The pretrained model in your Google drive is broken HOT 1
- train this
- 训练参数
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 danet.