Comments (3)
yes, i have found it too. a little confused.
Is the network different for different style ?
from fast-neural-style.
The models with instance normalization use a slightly different architecture than the ECCV16 models; they use half as many filters per layer, so they have a smaller file size.
The size of checkpoints increases slightly during training because in addition to the model the checkpoints also store a history of training and validation losses. You could reduce the size of checkpoints by stripping this history of training and validation losses, but this would probably not make a big difference.
In addition to model weights, Torch checkpoints also store tensors for the gradients of model weights; this makes checkpoints twice as big as they really need to be. It is possible to remove these gradient tensors before saving checkpoints, but this is annoying and somewhat error-prone so I have not implemented it here.
from fast-neural-style.
@jcjohnson Thank you. Do you mean set checkpoint_every
larger can slightly reduce the model size but the more important is remove the gradient tensors in the code. I think there is a solution is to write a script that can remove useless data, so that users can use it who need it.
from fast-neural-style.
Related Issues (20)
- cuda runtime error when training
- invalid argument: /path/to/output/file.h5
- Training image sizes
- train requirements.txt error 'ascii' codec can't decode byte 0xe2 in position 1178
- How to understand the gradient backward propagation of perceptual loss? HOT 1
- did you try it with nvidia jetson tx2 / nvidia xavier hardware?
- cannot open <starry_night.t7>
- Cannot run fast_neural_style.lua script(libjpeg library problem) HOT 1
- Diffrent results on diffrent machines HOT 1
- C# Implementation
- predict result is different when running opencv and fast_neural_style.lua script HOT 1
- get bad results after training candy
- unable to set v4l2 format: Invalid argument
- File.lua: unknown object HOT 2
- What is motivation of using 9x9 conv at first and last layer?
- tanh 150 constant - why? HOT 6
- could we apply fast-neural-transfer to image deformation?
- fork failed: cannot allocate memory HOT 1
- Problems with lua HOT 1
- Does anyone know the original source of the mosaic image?
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 fast-neural-style.