Re: And now for something different

[Gonz]

Bookmarked!

Thank you Juan.

--Gonz

On Wed, Apr 14, 2021 at 4:04 PM Juan Buhler  wrote:
>
> Gonz,
>
> In order to go from 2048D to 2D, there are a couple of techniques for
> dimensionality reduction out there. I'm using the most common one. Look
> here:
>
> https://lvdmaaten.github.io/tsne/
>
> j
>
> --
> Juan Buhler - http://www.juanbuhler.com
> --
> %(real_name)s Pentax-Discuss Mail List
> To unsubscribe send an email to pdml-le...@pdml.net
> to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
> the directions.



-- 
  "I think my ex-wife has weekly lessions with the Devil on how to
   be more evil.  I don't know how much she charges him."  - Emo Philips
--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.

Re: And now for something different

[Juan Buhler]

Gonz,

In order to go from 2048D to 2D, there are a couple of techniques for
dimensionality reduction out there. I'm using the most common one. Look
here:

https://lvdmaaten.github.io/tsne/

j

--
Juan Buhler - http://www.juanbuhler.com
--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.

Re: And now for something different

[Gonz]

It all sounds pretty straightforward, but I'm curious about the last
step of folding 2048D -> 2D.  Must involve some kind of clustering?
How is this done?  This seems key.

--gonz

On Sun, Apr 4, 2021 at 11:47 AM Juan Buhler  wrote:
>
> > Just out of curiosity, what was the input to the Neural Network?
> > Keywords, descriptions?
>
> No, it's just the pixels themselves. I'm using a pretrained convolutional
> neural network, or CNN. You know how Google Photos is able to separate
> photos into categories, with dogs, food, mountains, etc? That is done with
> a neural network of the same type.
>
> These CNNs will output the confidence they have that an image belongs to
> one of many classes they were trained for. But in the process they compute
> a vector that sort of encodes what "features" exist in the image. Features
> are things like lines, dots, patterns, and also combinations of things that
> might form "higher level features", like eyes, bicycle wheels, etc etc.
> These vectors are of very high dimension, in this case 2048.
>
> It turns out that points in this 2048-D space will be close to each other
> if the images they come from are similar to each other.
>
> The process I'm using computes and saves this vector for each image. That
> alone allows me to do image similarity search, by comparing these vectors.
>
> In order to make the plot, I use a technique that "folds" those 2048
> dimensions into two, so I can find a position for each image on the plane.
>
> Hopefully I succeeded in making that explanation not too technical?
>
> j
>
> --
> Juan Buhler - http://www.juanbuhler.com
>
>
> On Sun, Apr 4, 2021 at 1:53 AM  wrote:
>
> > Interesting Juan!
> >
> >
> > > On 3 Apr 2021, at 23:22, Juan Buhler  wrote:
> > >
> > > I made a plot of about 3000 of my photos (all posted to my photoblog over
> > > the years) according to positions in the plane that come from a neural
> > > network.
> > >
> > > Without getting into technical detail: images that are close to each
> > other
> > > are semantically similar to each other. So there are areas of photos with
> > > dogs, others with bicycles, on the beach, etc etc.
> > >
> > > https://twitter.com/juanbuhler/status/1378455676444270593
> > >
> > > To see the high res image and zoom in, look at the file directly:
> > >
> > > https://pbs.twimg.com/media/EyFA3LlU4Ag0QRQ?format=jpg=4096x4096
> > >
> >
> > Just out of curiosity, what was the input to the Neural Network?
> >
> > Keywords, descriptions?
> >
> >
> > > I thought it was an interesting way of seeing a collection of photos and
> > > discovering emerging visual themes. Also it's what I do for a living so I
> > > figured why not.
> > >
> >
> > Indeed, touching on ‘big data’ ;-)
> >
> >
> > Regards, JvW
> >
> > --
> > Jan van Wijk;   https://www.dfsee.com/gallery
> >
> > --
> > %(real_name)s Pentax-Discuss Mail List
> > To unsubscribe send an email to pdml-le...@pdml.net
> > to UNSUBSCRIBE from the PDML, please visit the link directly above and
> > follow the directions.
> --
> %(real_name)s Pentax-Discuss Mail List
> To unsubscribe send an email to pdml-le...@pdml.net
> to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
> the directions.



-- 
  "I think my ex-wife has weekly lessions with the Devil on how to
   be more evil.  I don't know how much she charges him."  - Emo Philips
--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.

Re: And now for something different

[pentax]

Hello Juan,

> On 4 Apr 2021, at 18:46, Juan Buhler  wrote:
> 
>> Just out of curiosity, what was the input to the Neural Network?
>> Keywords, descriptions?
> 
> No, it's just the pixels themselves. I'm using a pretrained convolutional
> neural network, or CNN. You know how Google Photos is able to separate
> photos into categories, with dogs, food, mountains, etc? That is done with
> a neural network of the same type.
> 
> These CNNs will output the confidence they have that an image belongs to
> one of many classes they were trained for. But in the process they compute
> a vector that sort of encodes what "features" exist in the image. Features
> are things like lines, dots, patterns, and also combinations of things that
> might form "higher level features", like eyes, bicycle wheels, etc etc.
> These vectors are of very high dimension, in this case 2048.
> 
> It turns out that points in this 2048-D space will be close to each other
> if the images they come from are similar to each other.
> 
> The process I'm using computes and saves this vector for each image. That
> alone allows me to do image similarity search, by comparing these vectors.
> 
> In order to make the plot, I use a technique that "folds" those 2048
> dimensions into two, so I can find a position for each image on the plane.
> 

Okay, interesting, thanks for explaining!

I have been doing something remotely similar with face-recognition on multiple 
live video-streams a few years ago, for supermarket customer-following systems 
...


> Hopefully I succeeded in making that explanation not too technical?
> 

Not at all, I am a programmer too, mainly making disk and filesystem recovery 
software, in plain ‘C’ ;-)


Regards, JvW


--
Jan van Wijk;   https://www.dfsee.com/gallery

--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.

Re: And now for something different

[Juan Buhler]

Here is another version, without overlap between photos:

https://twitter.com/juanbuhler/status/1379201237187395584
https://pbs.twimg.com/media/EyPn2IVUYAMv5BO?format=jpg=4096x4096

j

--
Juan Buhler - http://www.juanbuhler.com


On Sat, Apr 3, 2021 at 2:22 PM Juan Buhler  wrote:

>
> I made a plot of about 3000 of my photos (all posted to my photoblog over
> the years) according to positions in the plane that come from a neural
> network.
>
> Without getting into technical detail: images that are close to each other
> are semantically similar to each other. So there are areas of photos with
> dogs, others with bicycles, on the beach, etc etc.
>
> https://twitter.com/juanbuhler/status/1378455676444270593
>
> To see the high res image and zoom in, look at the file directly:
>
> https://pbs.twimg.com/media/EyFA3LlU4Ag0QRQ?format=jpg=4096x4096
>
> I thought it was an interesting way of seeing a collection of photos and
> discovering emerging visual themes. Also it's what I do for a living so I
> figured why not.
>
> Most of these were taken on Pentax cameras, so on topic! :)
>
> j
>
> --
> Juan Buhler - http://www.juanbuhler.com
>
--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.

Re: And now for something different

[John]

Depends on how they stack the bundles.

On 4/5/2021 08:58:36, ann sanfedele wrote:

Indeed.. $63,000,000 worth.
but I have to say I thought it was very beautiful

ann

On 4/5/2021 8:45 AM, John wrote:

There was something about "NFT" in the news recently.

On 4/3/2021 18:14:29, ann sanfedele wrote:

er. bad time for me to typo.. I meant NFT..  :-)

We will soon know who has to ask what I'm talking about...

Meanwhile - it is a handsome image by itself - rather Escheresque

ann


On 4/3/2021 6:07 PM, ann sanfedele wrote:

Sooo Juan, how much is the NFD file selling for?  :-)

ann

On 4/3/2021 5:22 PM, Juan Buhler wrote:

I made a plot of about 3000 of my photos (all posted to my photoblog over
the years) according to positions in the plane that come from a neural
network.

Without getting into technical detail: images that are close to each other
are semantically similar to each other. So there are areas of photos with
dogs, others with bicycles, on the beach, etc etc.

https://twitter.com/juanbuhler/status/1378455676444270593

To see the high res image and zoom in, look at the file directly:

https://pbs.twimg.com/media/EyFA3LlU4Ag0QRQ?format=jpg=4096x4096

I thought it was an interesting way of seeing a collection of photos and
discovering emerging visual themes. Also it's what I do for a living so I
figured why not.

Most of these were taken on Pentax cameras, so on topic! :)

j

--
Juan Buhler - http://www.juanbuhler.com
--









--
Science - Questions we may never find answers for.
Religion - Answers we must never question.
--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.

Re: And now for something different

[ann sanfedele]

Indeed.. $63,000,000 worth.
but I have to say I thought it was very beautiful

ann

On 4/5/2021 8:45 AM, John wrote:

There was something about "NFT" in the news recently.

On 4/3/2021 18:14:29, ann sanfedele wrote:

er. bad time for me to typo.. I meant NFT..  :-)

We will soon know who has to ask what I'm talking about...

Meanwhile - it is a handsome image by itself - rather Escheresque

ann


On 4/3/2021 6:07 PM, ann sanfedele wrote:

Sooo Juan, how much is the NFD file selling for?  :-)

ann

On 4/3/2021 5:22 PM, Juan Buhler wrote:
I made a plot of about 3000 of my photos (all posted to my 
photoblog over

the years) according to positions in the plane that come from a neural
network.

Without getting into technical detail: images that are close to 
each other
are semantically similar to each other. So there are areas of 
photos with

dogs, others with bicycles, on the beach, etc etc.

https://twitter.com/juanbuhler/status/1378455676444270593

To see the high res image and zoom in, look at the file directly:

https://pbs.twimg.com/media/EyFA3LlU4Ag0QRQ?format=jpg=4096x4096

I thought it was an interesting way of seeing a collection of 
photos and
discovering emerging visual themes. Also it's what I do for a 
living so I

figured why not.

Most of these were taken on Pentax cameras, so on topic! :)

j

--
Juan Buhler - http://www.juanbuhler.com
--






--
ann sanfedele photography
https://annsan.smugmug.com
https://www.cafepress.com/+ann-sanfedele+gifts
https://www.lulu.com/spotlight/annsan
https://www.createphotocalendars.com/Shop/annsanfedelecalendarsandbooks
--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.

Re: And now for something different

[John]

There was something about "NFT" in the news recently.

On 4/3/2021 18:14:29, ann sanfedele wrote:

er. bad time for me to typo.. I meant NFT..  :-)

We will soon know who has to ask what I'm talking about...

Meanwhile - it is a handsome image by itself - rather Escheresque

ann


On 4/3/2021 6:07 PM, ann sanfedele wrote:

Sooo Juan, how much is the NFD file selling for?  :-)

ann

On 4/3/2021 5:22 PM, Juan Buhler wrote:

I made a plot of about 3000 of my photos (all posted to my photoblog over
the years) according to positions in the plane that come from a neural
network.

Without getting into technical detail: images that are close to each other
are semantically similar to each other. So there are areas of photos with
dogs, others with bicycles, on the beach, etc etc.

https://twitter.com/juanbuhler/status/1378455676444270593

To see the high res image and zoom in, look at the file directly:

https://pbs.twimg.com/media/EyFA3LlU4Ag0QRQ?format=jpg=4096x4096

I thought it was an interesting way of seeing a collection of photos and
discovering emerging visual themes. Also it's what I do for a living so I
figured why not.

Most of these were taken on Pentax cameras, so on topic! :)

j

--
Juan Buhler - http://www.juanbuhler.com
--




--
Science - Questions we may never find answers for.
Religion - Answers we must never question.
--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.

Re: And now for something different

[Bob Pdml]

On 4 Apr 2021, at 17:47, Juan Buhler  wrote:


Just out of curiosity, what was the input to the Neural Network?
Keywords, descriptions?

No, it's just the pixels themselves. I'm using a pretrained convolutional
neural network,

[...]

In order to make the plot, I use a technique that "folds" those 2048
dimensions into two, so I can find a position for each image on the plane.

Hopefully I succeeded in making that explanation not too technical?

Easy-peasy!

https://tinyurl.com/MilagroJuan


--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.

Re: And now for something different

[Juan Buhler]

> Just out of curiosity, what was the input to the Neural Network?
> Keywords, descriptions?

No, it's just the pixels themselves. I'm using a pretrained convolutional
neural network, or CNN. You know how Google Photos is able to separate
photos into categories, with dogs, food, mountains, etc? That is done with
a neural network of the same type.

These CNNs will output the confidence they have that an image belongs to
one of many classes they were trained for. But in the process they compute
a vector that sort of encodes what "features" exist in the image. Features
are things like lines, dots, patterns, and also combinations of things that
might form "higher level features", like eyes, bicycle wheels, etc etc.
These vectors are of very high dimension, in this case 2048.

It turns out that points in this 2048-D space will be close to each other
if the images they come from are similar to each other.

The process I'm using computes and saves this vector for each image. That
alone allows me to do image similarity search, by comparing these vectors.

In order to make the plot, I use a technique that "folds" those 2048
dimensions into two, so I can find a position for each image on the plane.

Hopefully I succeeded in making that explanation not too technical?

j

--
Juan Buhler - http://www.juanbuhler.com


On Sun, Apr 4, 2021 at 1:53 AM  wrote:

> Interesting Juan!
>
>
> > On 3 Apr 2021, at 23:22, Juan Buhler  wrote:
> >
> > I made a plot of about 3000 of my photos (all posted to my photoblog over
> > the years) according to positions in the plane that come from a neural
> > network.
> >
> > Without getting into technical detail: images that are close to each
> other
> > are semantically similar to each other. So there are areas of photos with
> > dogs, others with bicycles, on the beach, etc etc.
> >
> > https://twitter.com/juanbuhler/status/1378455676444270593
> >
> > To see the high res image and zoom in, look at the file directly:
> >
> > https://pbs.twimg.com/media/EyFA3LlU4Ag0QRQ?format=jpg=4096x4096
> >
>
> Just out of curiosity, what was the input to the Neural Network?
>
> Keywords, descriptions?
>
>
> > I thought it was an interesting way of seeing a collection of photos and
> > discovering emerging visual themes. Also it's what I do for a living so I
> > figured why not.
> >
>
> Indeed, touching on ‘big data’ ;-)
>
>
> Regards, JvW
>
> --
> Jan van Wijk;   https://www.dfsee.com/gallery
>
> --
> %(real_name)s Pentax-Discuss Mail List
> To unsubscribe send an email to pdml-le...@pdml.net
> to UNSUBSCRIBE from the PDML, please visit the link directly above and
> follow the directions.
--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.

Re: And now for something different

[pentax]

Interesting Juan!


> On 3 Apr 2021, at 23:22, Juan Buhler  wrote:
> 
> I made a plot of about 3000 of my photos (all posted to my photoblog over
> the years) according to positions in the plane that come from a neural
> network.
> 
> Without getting into technical detail: images that are close to each other
> are semantically similar to each other. So there are areas of photos with
> dogs, others with bicycles, on the beach, etc etc.
> 
> https://twitter.com/juanbuhler/status/1378455676444270593
> 
> To see the high res image and zoom in, look at the file directly:
> 
> https://pbs.twimg.com/media/EyFA3LlU4Ag0QRQ?format=jpg=4096x4096
> 

Just out of curiosity, what was the input to the Neural Network?

Keywords, descriptions?


> I thought it was an interesting way of seeing a collection of photos and
> discovering emerging visual themes. Also it's what I do for a living so I
> figured why not.
> 

Indeed, touching on ‘big data’ ;-)


Regards, JvW

--
Jan van Wijk;   https://www.dfsee.com/gallery

--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.

Re: And now for something different

[ann sanfedele]

er. bad time for me to typo.. I meant NFT..  :-)

We will soon know who has to ask what I'm talking about...

Meanwhile - it is a handsome image by itself - rather Escheresque

ann


On 4/3/2021 6:07 PM, ann sanfedele wrote:

Sooo Juan, how much is the NFD file selling for?  :-)

ann

On 4/3/2021 5:22 PM, Juan Buhler wrote:
I made a plot of about 3000 of my photos (all posted to my photoblog 
over

the years) according to positions in the plane that come from a neural
network.

Without getting into technical detail: images that are close to each 
other
are semantically similar to each other. So there are areas of photos 
with

dogs, others with bicycles, on the beach, etc etc.

https://twitter.com/juanbuhler/status/1378455676444270593

To see the high res image and zoom in, look at the file directly:

https://pbs.twimg.com/media/EyFA3LlU4Ag0QRQ?format=jpg=4096x4096

I thought it was an interesting way of seeing a collection of photos and
discovering emerging visual themes. Also it's what I do for a living 
so I

figured why not.

Most of these were taken on Pentax cameras, so on topic! :)

j

--
Juan Buhler - http://www.juanbuhler.com
--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above 
and follow the directions.




--
ann sanfedele photography
https://annsan.smugmug.com
https://www.cafepress.com/+ann-sanfedele+gifts
https://www.lulu.com/spotlight/annsan
https://www.createphotocalendars.com/Shop/annsanfedelecalendarsandbooks
--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.

Re: And now for something different

[ann sanfedele]

Sooo Juan, how much is the NFD file selling for?  :-)

ann

On 4/3/2021 5:22 PM, Juan Buhler wrote:

I made a plot of about 3000 of my photos (all posted to my photoblog over
the years) according to positions in the plane that come from a neural
network.

Without getting into technical detail: images that are close to each other
are semantically similar to each other. So there are areas of photos with
dogs, others with bicycles, on the beach, etc etc.

https://twitter.com/juanbuhler/status/1378455676444270593

To see the high res image and zoom in, look at the file directly:

https://pbs.twimg.com/media/EyFA3LlU4Ag0QRQ?format=jpg=4096x4096

I thought it was an interesting way of seeing a collection of photos and
discovering emerging visual themes. Also it's what I do for a living so I
figured why not.

Most of these were taken on Pentax cameras, so on topic! :)

j

--
Juan Buhler - http://www.juanbuhler.com
--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.


--
ann sanfedele photography
https://annsan.smugmug.com
https://www.cafepress.com/+ann-sanfedele+gifts
https://www.lulu.com/spotlight/annsan
https://www.createphotocalendars.com/Shop/annsanfedelecalendarsandbooks
--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.

Re: And now for something different

[Daniel J. Matyola]

Very interesting.

Dan Matyola
*https://tinyurl.com/DJM-Pentax-Gallery
*



On Sat, Apr 3, 2021 at 5:23 PM Juan Buhler  wrote:

> I made a plot of about 3000 of my photos (all posted to my photoblog over
> the years) according to positions in the plane that come from a neural
> network.
>
> Without getting into technical detail: images that are close to each other
> are semantically similar to each other. So there are areas of photos with
> dogs, others with bicycles, on the beach, etc etc.
>
> https://twitter.com/juanbuhler/status/1378455676444270593
>
> To see the high res image and zoom in, look at the file directly:
>
> https://pbs.twimg.com/media/EyFA3LlU4Ag0QRQ?format=jpg=4096x4096
>
> I thought it was an interesting way of seeing a collection of photos and
> discovering emerging visual themes. Also it's what I do for a living so I
> figured why not.
>
> Most of these were taken on Pentax cameras, so on topic! :)
>
> j
>
> --
> Juan Buhler - http://www.juanbuhler.com
> --
> %(real_name)s Pentax-Discuss Mail List
> To unsubscribe send an email to pdml-le...@pdml.net
> to UNSUBSCRIBE from the PDML, please visit the link directly above and
> follow the directions.
>
--
%(real_name)s Pentax-Discuss Mail List
To unsubscribe send an email to pdml-le...@pdml.net
to UNSUBSCRIBE from the PDML, please visit the link directly above and follow 
the directions.