Comments (9)
And here are some example of what is generated :
from joligen.
it's already the 50+ epochs, and it seemed the model doesn't improve much. (the problem surely come from the lack of diversity of the training data 3568 synthetic/ 6519 realistic) but is there something i can do to improve the model performance ?
I use mask (not bounding box) for the training.
from joligen.
from joligen.
my train config file
seg_sem.json
from joligen.
I believe we had this conversation before, right ? This dataset cannot lead to much results IMO, I can find and resend my email about it if needed.
Algorithms cannot compensate for badly set data. There may be ways to find hyper-parameters that do better than others, but at the margin only.
from joligen.
If you wish to test on a dataset from the literature, gta5 to cityscapes is one, and there are others.
from joligen.
Is there a specific methodology? During our last meeting I think I heard that you "restart the training", Is it related to when the model is doing poorly at some epochs which is detected visually throught the loss function or is at a specific way of training or do you just train in one go and change parameters according to your results after a training is over?
from joligen.
I'll try on gtaV2cityscape as an external reference for the doability on this specific uc.
from joligen.
This is to illustrate my argument: synth data has no trees/natural life basically, so the discriminator is pushing for them on fake images. Which is not what the goal is here. This is because synth and real domain need to have a purpose one to the other in reality.
Also, classes between synth and real domains may not be the same, which is wrong and makes semantic conservation much more difficult.
(different colors mean different classes)
from joligen.
Related Issues (20)
- Example of a json file for training HOT 3
- Exception in dataloader.py HOT 3
- Preserving the semantics during translation HOT 6
- Using `--sampling-steps` in 'gen_single_image_diffusion.py` breaks the inference HOT 1
- A question about training on weather conditions HOT 13
- Issues encounter while training model on 4 gpus HOT 34
- How to train diffusion model on paired i2i dataset like style transfer? HOT 2
- Output image size when applying a model (inference) HOT 4
- Using TPUs HOT 1
- Unet_mha_ref_attn run training example
- inference unetref generator HOT 7
- Error when loading the dataset with Release 1.0.0 HOT 5
- Training with semantic segmentation error "NameError: name 'N_img_path' is not defined" HOT 2
- unet ref training preview and inference script HOT 4
- Adding logo(s) in AI-generated shirt HOT 3
- The 'ref-in' parameter is indeed mandatory. HOT 3
- problem training on master HOT 3
- Import images with paths.txt file in unaligned mode HOT 2
- BUG: AttributeError: 'float' object has no attribute 'clone' HOT 5
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 joligen.