Comments (6)
loss_adv_p is essentially the inverse loss of loss_D. We expect them to achieve a good balance during the adversarial training. Please refer to equation (1) and (4) in our paper. We use lambda_adv to control the balance point between loss_adv_p and loss_D. Does that answer your question?
from advsemiseg.
Great. You have mentioned that your task tries to minimize loss_D and maximize loss_adv_p. However, when we maximize loss_adv_p, the loss_seg_total = loss_seg+ lambdax loss_adv_p
in ep (2) tends to increase. But we want to minimize the eq (2). Does it make sense?
One more thing, your implementation use
You used
for param in model_D.parameters():
param.requires_grad = False
loss = loss_seg + args.lambda_adv_pred * loss_adv_pred
loss.backward()
Does it same as the below?
loss = loss_seg + args.lambda_adv_pred * loss_adv_pred
loss_seg.backward()
By delete the first two lines and change loss.backward() to loss_seg.backward()because loss_adv_pred does not do backward() so D not trained.
from advsemiseg.
from advsemiseg.
Thanks. I have updated something in the above question related to implementation. Could you also look at it? Thanks for your answer
from advsemiseg.
No. It's not equivalent. By doing that you are not performing the adversarial training since you are not minimizing loss_adv.
from advsemiseg.
@hfslyc : Thanks. I have one more question. In my case, the both loss_adv_p
and loss_D
are decreasing. What does happen in my case? Do we expect that loss_adv_p
increases and loss_D
decrease?
from advsemiseg.
Related Issues (20)
- some questions about datasets HOT 2
- Question about evaluation scheme HOT 1
- how to draw a loss curve?
- Some evaluation questions? HOT 2
- Can't recreate results for SL
- loss_semi < = 0.002 HOT 4
- IndexError: too many indices for array: array is 0-dimensional, but 1 were indexed HOT 1
- RuntimeError
- TypeError: 'range' object does not support item assignment HOT 2
- About dataset
- all losses are NaN
- Why there are two semi-supervisory control parameters: SEMI_START=5000,,,,,,,SEMI_START_ADV=0 HOT 1
- When loading model parameters during training, the program has been stuck without response
- Problem in deeplab model
- loss_ce gradually rises after falling
- Not able to reach pre-trained models HOT 2
- 关于5000次迭代前的训练 HOT 2
- Facing Issue for running Adversarial Semi-Segmentation code on Custom dataset or CityScapes dataset
- Quenstion on Loss
- Questions about evaluate_voc.py 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 advsemiseg.