Comments (3)
Maybe try with different learning rate? Are you using your own data?
from segan.
Yes, I use my own data. Loss during training has generally been very small and shows large and small.What's the matter?
from segan.
What do you mean by "shows large and small"? I suggest you start w/o the adversarial loss (e.g., use the generator with cross-entropy loss) to see if there are any bugs in the code. After running smoothly, you can move to the adversarial training.
from segan.
Related Issues (20)
- Reproducing the results HOT 3
- The loss of S and C optimization is different HOT 1
- How to configure the models and ground truth for multi-class segmentation?
- Why the discriminator output multiplies 2 and 4?
- Number of Learnable Parameters?
- why NetC.zero_grad()?
- WireframeRenderer
- Source code for multi-class segmentation requested HOT 1
- one of the variables needed for gradient computation has been modified by an inplace operation
- the link of dataset HOT 1
- Custom data set Discriminator loss tend to inf even with small learning rates
- there is an error in line 125 HOT 1
- I want to perform segmentation tasks on my own dataset, but there seems to be a problem with the Nets HOT 1
- Why do we need to clip gradient in netC? HOT 3
- pytorch version? HOT 1
- Errors HOT 1
- loss HOT 3
- Difficulties on reproducing the results HOT 2
- i got an error in the dataloader_val , raising an exception HOT 2
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 segan.