I've trained a net using Darkflow and now have the .pb files. I was wondering if it's possible (and if it is, how can it be done) to convert the files to .weight files for Darknet? I'd like to use Darknet with these files to classify images on Raspberry Pi.
I've been Googling but I see most people want to do the opposite.
Instead of weight file try .pb:
sudo ./darknet detector test cfg/coco.data cfg/yolov2.cfg <yourfile>.pb data/dog.jpg
Related
How could I read Garmin's .fit file on Linux. I'd like to use it for some data analysis but the file is a binary file.
I have visited http://garmin.kiesewetter.nl/ but the website does not seem to work.
Thanks
You can use GPSbabel to do this. It's a command-line tool, so you end up with something like:
gpsbabel -i garmin_fit -f {filename}.fit -o csv -F {output filename}.csv
and you'll get a text file with all the lat/long coordinates.
What's trickier is getting out other data, ie: if you want speed, time, or other information from the .fit file. You can easily get those into a .gpx, where they're in xml and human-readable, but I haven't yet found a single line solution for getting that data into a csv.
The company that created ANT made an SDK package available here:
https://www.thisisant.com/resources/fit
When unzipping this, there is a java/FitCSVTool.jar file. Then:
java -jar java/FitCSVTool.jar -b input.fit output.csv
I tested with a couple of files and it seems to work really well. Then of course the format of the csv can be a little bit complex.
For example, latitude and longitude are stored in semicircles, so it should be multiplied by 180/(2^31) to give GPS coordinates.
You need to convert the file to a .csv, the Garmin repair tool at http://garmin.kiesewetter.nl/ will do this for you. I've just loaded the site fine, try again it may have been temporarily down.
To add a little more detail:
"FIT or Flexible and Interoperable Data Transfer is a file format used for GPS tracks and routes. It is used by newer Garmin fitness GPS devices, including the Edge and Forerunner." From the OpenStreetMap Wiki http://wiki.openstreetmap.org/wiki/FIT
There are many tools to convert these files to other formats for different uses, which one you choose depends on the use. GPSBabel is another converer tool that may help. gpsbabel.org (I can't post two links yet :)
This page parses the file and lets you download it as tables. https://www.fitfileviewer.com/ The fun bit is converting the timestamps from numbers to readable timestamps Garmin .fit file timestamp
I've done the various steps to adapt CMU Sphinx using some recorded WAV files. Now where to the resulting files go?
I want to let each user on the system adapt CMU Sphinx to his own voice, so I don't want to store the files in /usr/local.
Is there a default directory or do I just have to specify them and their locations every time I run pocketSphinx?
Depending on the type of adaption you use, the resulting files can be either a transformation matrix which you specify with -mllr or a completely new model which is saved where you pointed out to. Adapted model has the same structure as the default one, so yes, you specify them and their locations every time your run the application. See the official tutorial for more information.
I have a folder of image file which have been compressed into .dat file. Since the .dat files are extremly huge(They are the microscopic image of the organ.), I don't really know what kind of tools that I can use to convert it into jpeg file. So the best case would that the whole image is split up into pieces, and I can get all the pieces of the image.
The ".dat" file suffix is used broadly, so you'll need to specify more details on what format/source software created the original data. As a guess, from a quick search of ".dat" format microscopy, these tools looks like they might be applicable to your domain:
http://gwyddion.net/
or
http://www.openmicroscopy.org/site/products/bio-formats
If you can't find a library for the format/languages you are using, then you'll need to find documentation of the file format, and write a converter (at least, the reading portion of the converter - you can use something like libjpeg to handle the writing portion.)
I want two compare two voice files and find difference between them.
Suppose I have an original file of a music track and another file that is read out of that music by me, I want two compare these two files and find difference between their phonemes. Actually the words aren't important for me, the important thing is similarity in phonemes and I want to find something like the percentage of similarity. I prefer to implement something with Python.
You could try audio fingerprinting using fpcalc in Chromaprint.
Chromaprint is the core component of the AcoustID project.
The audio fingerprinting is done using fpcalc in Chromaprint.
fpcalc should be placed in the same directory as the Python script.
Python bindings for Chromaprint acoustic fingerprinting and the Acoustid API.
https://pypi.python.org/pypi/pyacoustid
Bellow is an example article with python demo code.
Comparing Non-Identical Audio Files for Duplicate Content with Cross-Correlated Fingerprints
http://www.randombytes.org/audio_comparison.html
How does Chromaprint work?
http://oxygene.sk/2011/01/how-does-chromaprint-work/
I am aiming to combine multiple PDF files each with identical dimensions into one file.
I've seen how it is done with CGPDFContext. I am just curious if there are (better?) alternatives to this method on the Mac.
Let's say I have the option to use PDFs, TIFF, PNG or JPEG files as input. Would using a different input file type mean anything significant for the process, or it would be easier to go with PDF input?
I have use PDFDocument API and it is programmatically easier to use. It may need PDF files as input though.