Comments (6)
For your first question, I tried both scenarios and get similar results. Thus, you can train CycleGAN without perceptual loss. For the second one, the model is pertained with ImageNet.
from bdl.
For your first question, I tried both scenarios and get similar results. Thus, you can train CycleGAN without perceptual loss. For the second one, the model is pertained with ImageNet.
Thanks for quick reply! And I found it very slow to train cyclegan with perceptual loss(it may takes around a month in my situation, I mentioned this under another question ). So I'm suprised that you just spent 4 days. Did you use single GPU? or multi GPUS?
from bdl.
I use 4 gpus
from bdl.
I use 4 gpus
Thanks, that might be normal. The GPU I used is not compatible to teslaV100. Is it convenient for you to upload the first translation image? Anyway, It's also ok for not. While you train cyclegan with larger batchsize, is the initial learning rate you used same with standard cyclegan ?
from bdl.
You can train with less epochs. I upload the parameters I use. You can refer to it.
from bdl.
You can train with less epochs. I upload the parameters I use. You can refer to it.
Thanks very much! I've seen it.
from bdl.
Related Issues (20)
- Complete training procedure HOT 1
- Train CycleGAN HOT 2
- About the implementation HOT 1
- Number of common classes in Synthia dataset HOT 2
- About SYNTHIA to Cityscapes HOT 1
- Bug in the DeepLab ResNet101 atrous convolution forward function HOT 3
- does BDL support for pytorch 1.7 and cuda 10.2? HOT 1
- how to train own custom dataset? HOT 3
- error at running train.py for cyclegan HOT 2
- Inconsistency fix from CycleGan repository HOT 1
- problem about loss become nan HOT 1
- fineSize (cropSize) for Cycle-Gan HOT 5
- quick question HOT 5
- Issues with reproducing results using pre-trained weights on PyTorch 1.7 and CUDA 11 HOT 4
- About confidence threshold in SSL HOT 2
- Color of pseudolabels HOT 1
- Question about train,thanks
- Initialization of Deeplabv2 HOT 1
- Question about translation model (F)
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 bdl.