Hi people,
1. Laxminarayan has some very good suggestions. I think all of them are
possible with varying degree of success.
2. Liam, I am implementing a quite popular paper for image upscaling called
SRGAN.
3. Gerald, there would be a testing and validation datasets to gauge the
accuracy of the
All,
When people say "AI" here do they mean Neural Networks?
"Intelligent" algorithms have been implemented in GIMP for many years.
About 15 years ago, this algorithm got integrated into GIMP:
http://www.siox.org
Now, the reason I bring this is up is that any machine learning algorithm
needs
On Sat, 2019-03-30 at 07:40 +0530, Laxminarayan Kamath via gimp-
developer-list wrote:
> just dropping a couple of ideas here
[...]
Something like waifu2x would be fabulous to have in GIMP (a neural
network-based image upscaling algorithm).
slave liam (ankh on IRC)
--
Liam Quin - web slave
Hi,
[Disclaimer : 1)my knowledge of AI os limited 2) Just another Gimp user.
Not a Gimp dev]
just dropping a couple of ideas here
1) Back and white to colour:
If we train a NN on black and white images and their colour equivalents,
will it be able to generate colour photos fro, black and
On Mon, 2019-01-21 at 19:23 +0530, Maitraya Bhattacharyya via gimp-
developer-list wrote:
>
[...]
> Now to train these neural nets, I will have to prepare a dataset
> consisting
> of low resolution and high resolution images and divide them into
> training,
> testing and validation sets.
If it
Hello Tobias,
the plugin can definitely works on CPU only. I developed it on an old PC
without cuda-capable GPU. Tensorflow CAN run on CPU only!!!
A cuda-capable gpu card will perform the computation much faster, still the
plugin will work with no problems on CPU. :)
Regards,
Davide.
Il
Hi Davide,
that's cool. The problem I have is that you use Tensorflow and that is
CUDA/nvidia only. I have two notebooks but non with nvidia card. I
think it would be better to have a AI with a CPU fallback.
Regards,
Tobias
Am Mi., 20. Feb. 2019 um 17:54 Uhr schrieb Davide Sandona' via
Hi Davide,
I will use this code as reference as I have never made a plugin myself.
Thanks for this!
Maitraya
On Wed 20 Feb, 2019, 10:24 PM Davide Sandona' via gimp-developer-list <
gimp-developer-list@gnome.org wrote:
> Hello everyone,
>
> I too was interested about the integration of AI
Hello everyone,
I too was interested about the integration of AI algorithms into GIMP.
I created a GIMP plugin that implement the style transfer technique. You
can see the code in the following repository [1], as well as the
instructions to get it working. Into this plugin I have integrated two
Hi guys,
I have started working on the super-resolution plugin after going through
some tutorials on GANs. I will try to put some kind of update on my blog in
a month or so.
Thanks,
Maitraya.
On Mon, Jan 21, 2019 at 9:17 PM Maitraya Bhattacharyya <
maitraya.li...@gmail.com> wrote:
> Hi Elle,
>
On Mon, 2019-01-21 at 19:23 +0530, Maitraya Bhattacharyya via gimp-
developer-list wrote:
[...]
> Now to train these neural nets, I will have to prepare a dataset
> consisting
> of low resolution and high resolution images and divide them into
> training,
> testing and validation sets.
If it
Hi Elle,
I looked at the posts on discuss.pixls.us, and it seems that their approach
is quite different to what we are trying to achieve. They are mostly trying
to use multiple images or use traditional methods which don't yield very
good results.
Thanks,
Maitraya.
On Mon, Jan 21, 2019 at 9:12
On 1/21/19 10:01 AM, Elle Stone wrote:
I don't know if this is the same "super resolution", but FWIW the topic
has come up several times on discuss.pixls.us:
https://discuss.pixls.us/search?q=%20superresolution
My apologies, I wasn't very clear. discuss.pixls.us is a discussion
forum for
Hi Martin,
Thanks for the second link on Tensorlayer. if the license of the library is
compatible with GPL, there is no reason we cannot used their VGG19 network
but I don't think it is! I will still need a few weeks to create the image
dataset and then train this.
Thanks,
Maitraya.
On Mon,
Hi,
I already tried the first one, but it has not the quality I expected. Did
anybody tried the second one? The second one looks quite good :)
[1] https://github.com/alexjc/neural-enhance
[2] https://github.com/tensorlayer/srgan
Best regards,
Martin
Am Mo., 21. Jan. 2019 um 16:07 Uhr schrieb
On 1/21/19 8:53 AM, Maitraya Bhattacharyya via gimp-developer-list wrote:
super resolution
I don't know if this is the same "super resolution", but FWIW the topic
has come up several times on discuss.pixls.us:
https://discuss.pixls.us/search?q=%20superresolution
Best regards,
Elle Stone
Hi guys,
I think Casey's suggestion of super resolution is an excellent idea and
would be useful to a lot of people using GIMP. The two algorithms which
have been doing quite well are:
1. SRGAN: The relevant paper is at https://arxiv.org/abs/1609.04802 . This
has yielded some very nice results
Hi!
On Thu, Jan 17, 2019 at 12:14 PM Maitraya Bhattacharyya via
gimp-developer-list wrote:
> Dear devs,
>
> I have recently joined the mailing list because I wanted to contribute my
> two pennies to GIMP development (since I use it for my work). I had a look
> at the proposed plan for GIMP and
Hi again,
Something that I forgot to mention in the last email, here is a link for
fun: https://ai.googleblog.com/2017/04/teaching-machines-to-draw.html
M.
On Thu, Jan 17, 2019 at 6:43 PM Maitraya Bhattacharyya <
maitraya.li...@gmail.com> wrote:
> Hi Alexandre,
>
> I have yet to compile an
Hi Alexandre,
I have yet to compile an exhaustive list of algorithms but I am going to
mention two at the moment. We can compile a list later too:
1. Assisted background removal: The paper on this from Facebook is
https://arxiv.org/pdf/1703.06870.pdf . The ability to identify different
objects
On Thu, Jan 17, 2019 at 2:14 PM Maitraya Bhattacharyya wrote:
>
> Dear devs,
>
> I have recently joined the mailing list because I wanted to contribute my
> two pennies to GIMP development (since I use it for my work). I had a look
> at the proposed plan for GIMP and wondered if people would be
Dear devs,
I have recently joined the mailing list because I wanted to contribute my
two pennies to GIMP development (since I use it for my work). I had a look
at the proposed plan for GIMP and wondered if people would be interested in
including some popular AI algorithms for several image
22 matches
Mail list logo