Comments (5)
For 2): It depends on the task you would like to do. Sorry for not providing more useful information. If there are any other questions, feel free to reopen it.
from vqfr.
- The loss seems to have some problems. Have you changed any configurations and do you run the code in batch=16? The following is our log at 28.5K.
[epoch: 6, iter: 28,500, lr:(1.000e-04,)] [eta: 3 days, 12:00:50, time (data): 0.330 (0.003)] l_rec: 9.6236e-02 l_g_percep: 3.1971e-01 l_codebook: 6.3252e-02 l_total_g: 4.7919e-01
- We decide the 800K following the configuration of GFP-GAN and Restoreformer. Since the reconstruction results will be stable after about 500K, maybe you can try smaller epochs. In 8 x A100 machines, the total codebook training cost is about 3 day, 13 hours. If you use V100 machines, it may requires about twice training time.
from vqfr.
I changed the dataset from FFHQ to full images instead of just faces and I changed the color space to LAB. I also changed the configuration as well as I have 4 GPUs not 8 and their max memory is 24,5 GB each. So the batch size per gpu is 3. Is it a must that it is in RGB color space? and can it manage full images instead of just faces?
from vqfr.
It seems you try to adapt this codebase to other tasks. Because we have not try other tasks, we cannot give informative instructions. But I can provide several hints for you: 1) the lpips perceptual loss receives input of RGB color space. 2) The batch size need to be large for real images, otherwise, it requires a smaller learning rate and enlarges training epochs (refer to VQGAN).
from vqfr.
- Thank you so much, I can't believe I missed that.
- To increase the batch size I must decrease the input dimensions, how much will this impact the quality do you think?
from vqfr.
Related Issues (20)
- About how to get the validation dataset? HOT 1
- Can VQFR2 be placed in google drive too? HOT 1
- 4090 not worked... only CPU mode?
- config file for vqfr_v2 HOT 3
- Hi, training issue, "No object named 'VQFRModel' found in 'model' registry". HOT 2
- Unstable video effects HOT 3
- requirements.txt installs numpy>=1.21 citing numba, numba setup asks for numpy >= 1.21
- VQFR_v2 model not in Google Drive HOT 1
- 您好 v2版本的模型在哪呢,网盘里目前只有v1版本的么? HOT 1
- missed VQFR_v2.pth HOT 1
- TypeError: __init__() got an unexpected keyword argument 'in_dim' HOT 1
- How to convert model to onnx?
- In the whole process of training VQGAN, the PSNR was only 20
- Failed inference for VQFR: CUDA error: CUBLAS_STATUS_NOT_SUPPORTED when calling `cublasSgemmStridedBatched...
- 关于FFHQ训练集 HOT 3
- 关于option:Linux
- 训练报错
- vqfrv1训练效果不好
- How to train FFHQ on 1024x1024 resolution?
- eye color change
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 vqfr.