Comments (11)
On the same system, is the Torch implementation or this implementation faster? better? Anyone have comparisons?
from chainer-fast-neuralstyle.
@igorbarinov what's the difference between instance nomalization and batchnorm with batchsize = 1 ?
from chainer-fast-neuralstyle.
@igorbarinov got it. instance normalization only normalized in spatial not cross feature map and batch
from chainer-fast-neuralstyle.
@austingg Have you tried it? I think it does the same thing with batch normalization when you set batchsize = 1
from chainer-fast-neuralstyle.
@bucktoothsir I haven't tried. but batchsize = 1 still normalize cross the feature maps. instance normalization only do normalization within the feature map plane. As @yusuketomoto say, batchsize >=2 have some problem, i do all my experiments with batchsize = 1
from chainer-fast-neuralstyle.
@bucktoothsir sorry . After i checked the paper, i found batchsize = 1 is instance normalization.
from chainer-fast-neuralstyle.
Are you sure ? According to the paper that would mean that using batchsize=1 yields better results than batchsize >= 2
from chainer-fast-neuralstyle.
@ttoinou batch normalization is across instances, however, when batch size = 1, there is only one instance. You can also implement multi batch training with normaliztion within instance.
from chainer-fast-neuralstyle.
From the paper we can see the effect is greatly improved. Anybody have the implement in python, I can test it.
from chainer-fast-neuralstyle.
@logic1988 : Yes they updated their project yesterday with instance normalization with torch ! https://github.com/DmitryUlyanov/texture_nets
@austingg : Great so there's still some hope to get the training faster by fixing the batchsize issue (I guess that loading images, resizing them and giving them to the GPU would be faster in batch, no ? there would be less CPU <-> GPU communication)
from chainer-fast-neuralstyle.
There are a great Torch Implementation released by jcjohnson a few days ago.
https://github.com/jcjohnson/fast-neural-style
In addition to the original method, the new method inspired by the the paper [Instance Normalization: The Missing Ingredient for Fast Stylization] has been implemented.
The latter seems to have a better result and faster speed than the former.
It said that:
These models use the same architecture as those used in our paper, except with half the number of filters per layer and with instance normalization instead of batch normalization. Using narrower layers makes the models smaller and faster without sacrificing model quality.
How to modify the corresponding code in this project? @yusuketomoto
from chainer-fast-neuralstyle.
Related Issues (20)
- kanagawa
- the result is dark when it is used for super resolution
- Is there a style size?
- why do you set batch_size equal 1 HOT 1
- OutOfMemoryError when generate on Azure ND6 VM
- RuntimeError: CUDA environment is not correctly set up
- cupy.cuda.compiler.CompileException: nvrtc: error: failed to load builtins HOT 5
- LC_RPATH @executable_path error or libnvrtc-builtins.dylib error HOT 5
- How much is the proper training epoch?
- hello! can you code Fast Neural Style Transfer with Arbitrary Style ? HOT 6
- Memory error without GPU. HOT 1
- ValueError: test argument is not supported anymore. Use chainer.using_config HOT 5
- error in run train.py
- Style transfer between any two images - iOS App needs beta tester HOT 6
- volatile argument is not supported anymore. Use chainer.using_config HOT 10
- Output size few pixels smaller
- Artx - iOS App that transfer styles between any two images HOT 4
- how to download vgg16 and setup it ?
- error in sh setup_model.sh HOT 1
- RuntimeError: CUDA environment is not correctly set up 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 chainer-fast-neuralstyle.