Comments (4)
hfslyc
commented on June 5, 2024
For the segmentation network, the batch size is 10. However, for discriminator, we have 10 predictions from the segmentation network and 10 gt maps from the unlabeled data.
from advsemiseg.
John1231983
commented on June 5, 2024
Yes. So I am wondering about the discriminator network. It combined of two losses. Each loss takes 10 images a batch, so what is the batch size of the combined loss- loss real and loss fake?
from advsemiseg.
hfslyc
commented on June 5, 2024
If you want to have a specific number of batch size, I would say 10.
Because in normal GAN training, when we talk about batch size, it's usually
referring to the batch size of the generator, not the discriminator.
…On Wed, Jul 11, 2018 at 1:12 AM John1231983 ***@***.***> wrote:
Yes. So I am wondering about the discriminator network. It combined of two
losses. Each loss takes 10 images a batch, so what is the batch size of the
combined loss- loss real and loss fake?
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#13 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AKhYAWqTfgCyhjE8gvwFtH19JiA3SRLZks5uFbNlgaJpZM4VI8Bp>
.
from advsemiseg.
hfslyc
commented on June 5, 2024
if there is no further question, I'm closing this issue :)
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.