Welcome to Doom9's Forum, THE in-place to be for everyone interested in DVD conversion.

Before you start posting please read the forum rules. By posting to this forum you agree to abide by the rules.

 

Go Back   Doom9's Forum > Announcements and Chat > General Discussion

Reply
 
Thread Tools Search this Thread Display Modes
Old 3rd January 2018, 18:07   #1  |  Link
feisty2
I'm Siri
 
feisty2's Avatar
 
Join Date: Oct 2012
Location: Los Angeles, California
Posts: 2,119
any idea how to port a keras model to a vaporsynth plugin

I'm still far far away from getting my super resolution neural net done, the full model has around 40 million parameters and I have yet trained 100k of them with just one iteration of 2.5 million image samples, it's still pretty early stage cuz it's just one iteration of backprop and I only trained the low level residual part of the full model yet, the results are very "raw" and far far away from completion (it's now just one iteration for 100k parameters, I'm planning on 10 ~ 15 iterations for 40m parameters), but it already outperformed stuff like nnedi3 and waifu2x, I just thought I might as well write a vaporsynth plugin for it but I don't know where to get started, the model was coded with keras, a high level tensorflow library, in Python, it has tons of dependencies like cudnn, tensorflow and installing tensorflow, especially the gpu version, is a real pain, how can make it like waifu2x, a single plugin without any dependencies?

also if ur interested in the early stage raw results
small image

2x upscale with non-ringing spline

2x upscale with nnedi3

2x upscale with waifu2x

early stage result of my model
__________________
If I got new ideas, will post here: https://github.com/IFeelBloated
feisty2 is offline   Reply With Quote
Old 4th January 2018, 01:41   #2  |  Link
WolframRhodium
Registered User
 
Join Date: Jan 2016
Posts: 56
To the best of my knowledge, there seems no straightforward solution to write a single plugin of CNN without many dependencies.
I'm not sure whether the C++ support of TF on Windows is good or not, but for MXNet, a plugin was released building upon the official C++ support, while the model was trained in Python. The dependencies of it are enormous. There are also many convertors to transform a model in one framework to another, but I'm not sure whether they work well.
Another naive solution is to directly call the model inside Python, but since std.ModifyFrame is a single thread plugin, it behaves like a performance bottleneck.

Last edited by WolframRhodium; 4th January 2018 at 02:03.
WolframRhodium is offline   Reply With Quote
Old 6th January 2018, 21:43   #3  |  Link
amayra
Quality Checker
 
amayra's Avatar
 
Join Date: Aug 2013
Posts: 183
vapoursynth*
__________________
I love Doom9
amayra is offline   Reply With Quote
Old 7th January 2018, 13:12   #4  |  Link
feisty2
I'm Siri
 
feisty2's Avatar
 
Join Date: Oct 2012
Location: Los Angeles, California
Posts: 2,119
Quote:
Originally Posted by amayra View Post
vapoursynth*
and the commonwealth spelling should die
__________________
If I got new ideas, will post here: https://github.com/IFeelBloated
feisty2 is offline   Reply With Quote
Old 8th January 2018, 02:29   #5  |  Link
raffriff42
Retried Guesser
 
raffriff42's Avatar
 
Join Date: Jun 2012
Posts: 1,307
Sounds like a fascinating project! It looks like installing the CPU version of TensorFlow is not that hard, basically one Python command. This eliminates the need for cuDNN as well. Once your project is released, maybe someone will help by writing an install program for the GPU version.
Quote:
https://www.tensorflow.org/install/install_windows

If your system does not have a NVIDIAŽ GPU, you must install this [CPU] version. Note that this version of TensorFlow is typically much easier to install (typically, in 5 or 10 minutes), so even if you have an NVIDIA GPU, we recommend installing this version first.

https://www.tensorflow.org/install/i...ith_native_pip
To install TensorFlow, start a [Python] terminal. Then issue the appropriate pip3 install command in that terminal. To install the CPU-only version of TensorFlow, enter the following command:

C:\> pip3 install --upgrade tensorflow
raffriff42 is offline   Reply With Quote
Old 9th January 2018, 06:46   #6  |  Link
amayra
Quality Checker
 
amayra's Avatar
 
Join Date: Aug 2013
Posts: 183
Quote:
Originally Posted by feisty2 View Post
and the commonwealth spelling should die
commonwealth*
__________________
I love Doom9
amayra is offline   Reply With Quote
Old 9th January 2018, 09:27   #7  |  Link
feisty2
I'm Siri
 
feisty2's Avatar
 
Join Date: Oct 2012
Location: Los Angeles, California
Posts: 2,119
Quote:
Originally Posted by amayra View Post
commonwealth*
It's spelled "vapor" in Latin so "vapour" is simply incorrect
Now stop trolling and stay on topic
__________________
If I got new ideas, will post here: https://github.com/IFeelBloated
feisty2 is offline   Reply With Quote
Old 29th January 2018, 12:39   #8  |  Link
ChaosKing
Registered User
 
Join Date: Dec 2005
Location: Germany
Posts: 217
Google released Tensorflow 1.5: easier integration / installation, built-in CUDA support, a lite version of TF. Maybe it's easier to distribute now as a plugin...

https://developers.googleblog.com/20...orflow-15.html
__________________
Search and denoise
ChaosKing is offline   Reply With Quote
Reply

Thread Tools Search this Thread
Search this Thread:

Advanced Search
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT +1. The time now is 01:15.


Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2018, vBulletin Solutions Inc.