I want to use Weka to do linear regression. I have already writing the java program to create a .arff dataset with all input features. I opened the .arff file. Under classify, I click "choose" under classifier and tried to find the linear regression but it is blank. I know it is suppose to have a list of algorithms when click choose, but I found blank page. I would like to know is there anything wrong with my operation or my weka installation?
There should be a drop down window with a list of classifiers. You may want to check your Weka installation, Java installation, and maybe your resolution / dpi scaling (maybe try a lower resolution if you are on a high dpi screen, or 100% / normal dpi scaling) to see if there is a problem with the way Weka is rendering the GUI.
Related
I am working on a pytorch project, where I’m using a webcam video stream. An object detector is used to find objects within the frame and each box is given an id by a tracker. Then, I want to analyse each bounding box with a CNN-LSTM and classify it (binary classification) based on the previous frame sequence of that box (for the last 5 frames). I want the program to run a close to real-time as possible.
Currently I am stuck with the CNN-LSTM part of my problem - the detector and tracker are working quite well already.
I am a little bit clueless on how to approach this task. Here are the questions I have:
1) How does inferencing work in this case? Do I have to save np arrays for each bounding box containing the last 5 frames, then add the current frame and delete the oldest one? Then use the model for each bounding box that is in the current frame. This way sounds very slow and inefficient. Is there a faster or easier way?
2) Do you have any tipps for creating the dataset? I have a couple of videos with bounding boxes and labels. Should I loop through the videos and save save each frame sequence for each bounding box in a new folder, together with a csv that contains the label? I have never worked with an CNN-LSTM, so I don’t know how to load the data for training.
3) Would it be possible to use the extracted features of the CNN in parallel? As mentioned above, The extracted features should be used by the LSTM for a binary classification problem. The classification is only needed for the current frame. I would like to use an additional classifier (8 classes) based on the extracted CNN features, also only for the current frame. For this classifier, the LSTM is not needed.
Since my explaining propably is very confusing, the following image hopefully helps with understanding what I want to build:
Architecture
This is the architecture I want to use. Is this possible using Pytorch? So far, I only worked with CNNs and LSTM seperately. Any help is apprechiated :)
I wish to display an image through my projector via MATlab. The projected image should be full sized without any figure handle bars (menu bar, the grey stuff which encompasses a figure etc).
Similar to a normal presentation when the projector projects the complete slide or image, I want to do the same using MATlab as my platform. Any thoughts or idea? Can we access the projector using MATlab? My first thoughts were to send data to the corresponding printer IP but that doesn't seem to work :/
If you know the relevant C++ command or method to do this, please suggest a link or a library, so that I may try and import it on my MATlab platform.
Reason for doing this: Projector-Camera calibration for photo-metric correction of my projector display output.
Assuming your projector is set as a second display, you can do something very simple. Get the monitor position information and set the figure frame to be the monitor size
// plot figure however you want
monitorFrames = get(0,'MonitorPositions');
secondMonitor = monitorFrames(2,:);
secondMonitor(3) = secondMonitor(3)-monitorFrames(1,3);
set(gcf,'Position',secondMonitor);
This will put the figure window onto the second monitor and have it take up the whole screen.
You can then use this to do whatever calibration you need, and shift this window around as necessary.
NOTE:
In no way am I saying this is the ideal solution. It is quick and dirty, and will not use any outside libraries.
UPDATE
If the above solution does not suit your specific needs, what you could always do is save the plot as an image, then have your MATLAB script, call a c++ script that opens the image and makes it full screen.
This is non-trivial. For Windows you can use the WindowAPI submission to the MATLAB File Exchange. With the WindowAPI function installed you can do
WindowAPI(FigH, 'Position', 'full');
For Mac and Linux you can use wrappers around OpenGL to do low level plotting, but you cannot use standard MATLAB figure windows. One nice implementation is PsychToolbox.
I am using the GDAL C++ library to reclassify raster map images and then create an output image of the new data. However when I create the new the new image and open it, the classification values don't seem to have a color defined, so I just get a black image. I can fix this by going into the image properties and setting a color for each of the 10 classification values I'm using, but that is extremely time consuming for the amount of maps and trials I am doing.
My question is, is there a way to set metadata info through the GDAL API to define a color for each classification value? Just the name of the right function would be great, I can figure it out from there.
I have tried this using ArcGIS and QuantumGIS, and both have the same problem. Also the file type I am using is Erdas Imagine (called "HFA" in GDAL).
You can use SetColorTable() method on your raster band. Easiest to do is to fetch one pre-existing raster using GetColorTable(), and pass it to your new raster.
What kind of debugging is available for image processing/computer vision/computer graphics applications in C++? What do you use to track errors/partial results of your method?
What I have found so far is just one tool for online and one for offline debugging:
bmd: attaches to a running process and enables you to view a block of memory as an image
imdebug: enables printf-style of debugging
Both are quite outdated and not really what I would expect.
What would seem useful for offline debugging would be some style of image logging, lets say a set of commands which enable you to write images together with text (probably in the form of HTML, maybe hierarchical), easy to switch off at both compile and run time, and the least obtrusive it can get.
The output could look like this (output from our simple tool):
http://tsh.plankton.tk/htmldebug/d8egf100-RF-SVM-RBF_AC-LINEAR_DB.html
Are you aware of some code that goes in this direction?
I would be grateful for any hints.
Coming from a ray tracing perspective, maybe some of those visual methods are also useful to you (it is one of my plans to write a short paper about such techniques):
Surface Normal Visualization. Helps to find surface discontinuities. (no image handy, the look is very much reminiscent of normal maps)
color <- rgb (normal.x+0.5, normal.y+0.5, normal.z+0.5)
Distance Visualization. Helps to find surface discontinuities and errors in finding a nearest point. (image taken from an abandoned ray tracer of mine)
color <- (intersection.z-min)/range, ...
Bounding Volume Traversal Visualization. Helps visualizing a bounding volume hierarchy or other hierarchical structures, and helps to see the traversal hotspots, like a code profiler (e.g. Kd-trees). (tbp of http://ompf.org/forum coined the term Kd-vision).
color <- number_of_traversal_steps/f
Bounding Box Visualization (image from picogen or so, some years ago). Helps to verify the partitioning.
color <- const
Stereo. Maybe useful in your case as for the real stereographic appearance. I must admit I never used this for debugging, but when I think about it, it could prove really useful when implementing new types of 3d-primitives and -trees (image from gladius, which was an attempt to unify realtime and non-realtime ray tracing)
You just render two images with slightly shifted position, focusing on some point
Hit-or-not visualization. May help to find epsilon errors. (image taken from metatrace)
if (hit) color = const_a;
else color = const_b
Some hybrid of several techniques.
Linear interpolation: lerp(debug_a, debug_b)
Interlacing: if(y%2==0) debug_a else debug_b
Any combination of ideas, for example the color-tone from Bounding Box Visualization, but with actual scene-intersection and lighting applied
You may find some more glitches and debugging imagery on http://phresnel.org , http://phresnel.deviantart.com , http://picogen.deviantart.com , and maybe http://greenhybrid.deviantart.com (an old account).
Generally, I prefer to dump bytearray of currently processed image as raw data triplets and run Imagemagick to create png from it with number e.g img01.png. In this way i can trace the algorithms very easy. Imagemagick is run from the function in the program using system call. This make possible do debug without using any external libs for image formats.
Another option, if you are using Qt is to work with QImage and use img.save("img01.png") from time to time like a printf is used for debugging.
it's a bit primitive compared to what you are looking for, but i have done what you suggested in your OP using standard logging and by writing image files. typically, the logging and signal export processes and staging exist in unit tests.
signals are given identifiers (often input filename), which may be augmented (often process name or stage).
for development of processors, it's quite handy.
adding html for messages would be simple. in that context, you could produce viewable html output easily - you would not need to generate any html, just use html template files and then insert the messages.
i would just do it myself (as i've done multiple times already for multiple signal types) if you get no good referrals.
In Qt Creator you can watch image modification while stepping through the code in the normal C++ debugger, see e.g. http://labs.qt.nokia.com/2010/04/22/peek-and-poke-vol-3/
Does anyone know of a c++ library for taking an image and performing image recognition on it such that it can find letters based on a given font and/or font height? Even one that doesn't let you select a font would be nice (eg: readLetters(Image image).
I've been looking into this a lot lately. Your best is simply Tesseract. If you need layout analysis on top of the OCR than go with Ocropus (which in turn uses Tesseract to do the OCR). Layout analysis refers to being able to detect position of text on the image and do things like line segmentation, block segmentation, etc.
I've found some really good tips through experimentation with Tesseract that are worth sharing. Basically I had to do a lot of preprocessing for the image.
Upsize/Downsize your input image to 300 dpi.
Remove color from the image. Grey scale is good. I actually used a dither threshold and made my input black and white.
Cut out unnecessary junk from your image.
For all three above I used netbpm (a set of image manipulation tools for unix) to get to point where I was getting pretty much 100 percent accuracy for what I needed.
If you have a highly customized font and go with tesseract alone you have to "Train" the system -- basically you have to feed a bunch of training data. This is well documented on the tesseract-ocr site. You essentially create a new "language" for your font and pass it in with the -l parameter.
The other training mechanism I found was with Ocropus using nueral net (bpnet) training. It requires a lot of input data to build a good statistical model.
In terms of invoking Tesseract/Ocropus are both C++. It won't be as simple as ReadLines(Image) but there is an API you can check out. You can also invoke via command line.
While I cannot recommend one in particular, the term you are looking for is OCR (Optical Character Recognition).
There is tesseract-ocr which is a professional library to do this.
From there web site
The Tesseract OCR engine was one of the top 3 engines in the 1995 UNLV Accuracy test. Between 1995 and 2006 it had little work done on it, but it is probably one of the most accurate open source OCR engines available
I think what you want is Conjecture. Used to be the libgocr project. I haven't used it for a few years but it used to be very reliable if you set up a key.
The Tesseract OCR library gives pretty accurate results, its a C and C++ library.
My initial results were around 80% accurate, but applying pre-processing on the images before supplying in for OCR the results were around 95% accurate.
What is pre-preprocessing:
1) Binarize the bitmap (B&W worked better for me). How it could be done
2) Resampling your image to 300 dpi
3) Save your image in a lossless format, such as LZW TIFF or CCITT Group 4 TIFF.