Comments (5)
For SE Cycle GAN, we add a loss in Cycle GAN during the reconstruction process.
In practice, we add a .py file and modify the model file.
Considering the minor improvement based on Cycle GAN, we provide some related files.
SE CycleGAN.zip
pytorch_ssim: loss computation.
cycle_gan_model.py: SE Cycle GAN model file
filter.py: Scene Regulization.
from gcc-sfcn.
Because of many deadlines in March and April, we don't have enough time to check the entire SE Cycle GAN code and release it. After April, we will try our best to open source it ASAP.
If you have any problems during training SE Cycle GAN, you can submit issues or send email to me: [email protected]. Thanks for your attention!
from gcc-sfcn.
Thanks a lot @gjy3035 that's very helpful! Would it be okay if you provide the hyperparameters you used with Cycada/SSIM?
For example,
- the lambda in the reconstruction loss;
- the crop size of the input image;
- the batch size; and
- the network architectures of the discriminators and generators?
Thanks a lot for your engagement! :)
from gcc-sfcn.
Other settings are followed by pix2pix's (pytorch 0.3.1) default configuration (the paper also mentions it). To be specific,
- lambda is 10.0;
- size setting:
- pre process: resize GCC to 540*960
- training: crop size 360*360
- batch size is 2 on two 1080Ti GPUs (you may adopt a larger value on Titan V or other high-performance devices);
- same as the default selection: basic and resnet_9blocks
Here, we provide the opt.txt for you.
opt.txt
Two key setting:
loadSize: 540
: height size for pre processing;
resize_or_crop: scale_height_and_crop
: keeping the ratio and resize GCC to height of 540, i.e., the entire resolution is 540*960 (you may add some code similar to "scale_width_and_crop" in data/base_dataset.py
).
from gcc-sfcn.
I wonder if the process of generating realistic GCC images are as follows:
- use 'scale_height_and_crop' to get 360*360 patches for CycleGAN training as your opt.txt above.
- use trained netG to get realistic GCC images with 540*960.
Thank you.
from gcc-sfcn.
Related Issues (20)
- Cannot reproduce the results for SHTA and UCF-QNRF dataset with cyclegan translated images
- How can I use the GCC dataset in my training process? HOT 1
- How to Accelerate Operation? HOT 1
- Idea: combine supervised and domain adaptation methods HOT 4
- RuntimeError: CUDNN_STATUS_INTERNAL_ERROR HOT 2
- When I want to train with my own data set, I get the following error
- IndexError happend in training HOT 1
- The segmentation file generated by the code of mcnn?
- Test my own data HOT 1
- .csv file doesn't exit when I run the python text.py HOT 1
- flops and params of the model ?
- Is this okay that you validate on test set? HOT 1
- Why divide predicted result by 100 in test.py? HOT 1
- where “”resnet101-5d3b4d8f.pth“”?? HOT 2
- What is the configuration of your computer for experiment? HOT 1
- SSIM loss
- What is the speed of the network ?
- Final model for the ShanghaiTech B dataset
- Crowd Counting problems
- where is the final model?can i test the model on my own picture directly? HOT 3
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 gcc-sfcn.