Comments (4)
Given one input image, we sample 19 pairs of outputs (randomly sample two style vectors and generate two images). We then compute the distance between two output images and get an average.
from munit.
Just for making sure, you generate the output images with random two style vectors and do this process 19 times, get 19 pairs of the output images and compute the distance of each pair and get an average finally. Do I understand correctly?
Thank you!
from munit.
Yes.
from munit.
So sampling 38 styles in one time is equal to sampling 19 pairs?
from munit.
Related Issues (20)
- How to implement MUNIT with K Fold Cross Validation?
- Question about Multi-GPU training on single machine HOT 4
- Can you use non-standardised dataset for training?
- Checkpoint images examples?
- Can i do train grayscale-imageset?
- Pytorch version >=1.0 How to load VGG16 pretrain in VGG16.T7? HOT 1
- Experiment of using Instance Normalization vs Layer Normalization on Decoder HOT 8
- AdaptiveInstanceNorm2d and the LayerNorm misunderstand
- May I ask if everyone will prompt "Warning: NaN or Inf found in input tensor." during runtime? HOT 1
- Questions about batch_size and GPU memory usage
- loss Nan
- How to only generate a single image
- style transfer
- Ideas to speed up training phase
- Missing max pooling layer in the Vgg16 network structure
- outputs = (outputs + 1) / 2. in test code HOT 1
- inception checkpoint? HOT 3
- Ŕ
- summer2winter_yosemite checkpoint?
- Pretrained Inception Network HOT 1
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 munit.