#DIGIKAM ICO GENERATOR#
There are far more powerful AI systems available, but we’ll use one that allows normal people to play with it, caption generator on github: Next we use AI to reduce the image to a symbolic semantic representation. We can start with the a generic image from Wikipedia: So now lets try a little AI assisted vector quantization of images. If a person skilled at drawing were to attempt to represent this coded reference visually, it is likely the result would be recognizable to others as a representation of the text that is, the text is an extremely compact symbolic representation of an image.
#DIGIKAM ICO SERIES#
The underlying mechanism is a sort of vector quantization where the text represents a series of vectors that semantically reference complex culturally shared elements that form a type of codebook. I’m sure each person reading this develops an internal model, likely some combination of a snug, warm indoor Christmas scene while outside a storm raged, or something to that effect derived from the shared cultural semantic representation: a scene with a great deal of detail and complexity, despite the very short text string. It was a dark and stormy night and all through the house not a creature was stirring, not even a mouse. This script is heavily derived from the script written by Marcin Sochacki and Ulrik Stervbo.Here disclosed is a novel compression technique I call Deep Learning Semantic Vector Quantization (DLSVC) that achieves in this sample 9,039:1 compression! Compare this to JPEG at about 10:1 or even HEIC at about 20:1, and the absolutely incredible power of DL image compression becomes apparent.īefore I disclose the technique to achieve this absolutely stunning result, we need to understand a bit about the psychovisual mechanisms that are being exploited. If you want to change the default image size (1280x1024) you can change the width and height parameters in the script's source. If you want to upload images with different tag, just change the -t parameter. This command will upload all photos tagged with "web" in the digiKam. $ python digikam_picasa.py -u -p secret -a NewAlbum -t web -d /media/data/photos/digikam3.db It is located in the root of directory digiKam uses to store the images (Settings > Configure > Albums > Album Library Path): You need to specify the the digikam's database file - digikam3.db. Now, lets upload the photos tagged with "web" in the digikam. This command will upload the image IMG_0001.JPG from the current directory into a new album called NewAlbum.
$ python digikam_picasa.py -u -p secret -a NewAlbum -f IMG_0001.JPG All you need to do is to specify the credentials for accessing the service (username, password), the album name and the files: Lets try to upload few images from file system first.
#DIGIKAM ICO DOWNLOAD#
#DIGIKAM ICO INSTALL#
In Ubuntu all of them happen to be a part of standard python2.5 package, but in other distributions you might have to install additional packages. It has several dependencies: ElementTree, httplib, urllib modules. Download the gdata-python-client library tar ball.It is optional (but highly recommended) to install The last package (jhead) is required to copy metadata from original images to resized ones. $ sudo apt-get install python python-imaging python-pysqlite2 jhead If you are running Ubuntu Linux it is easy as: Make sure you have Python and required library packages.The script also supports uploading files from the file system It utilizes the gdata-python-client API from Google to upload the photos, Python Imaging Library (PIL) for resizing and pysqlite for accessing the digiKam database. The script also resizes the images to a resolution suitable for viewing on a screen (1280x1024) to save space and speed up the upload. "web") and then run a script that creates new album in your Picasa Web account and uploads the tagged photos automatically. The idea is pretty simple - tag the photos inside digiKam with specific tag (e.g. This simple python script allows batch uploading of photos from digiKam photo organizer to Picasa Web Albums service.