I am trying to run CNTK object detecion example on PascalVoc pretrained dataset. I run all required scripts in fastrcnn and get the visual output for the test data defined in dataset. Now I want to test network on my own image, how can I do that?
For Fast R-CNN you need a library that generates candidate ROIs (regions of interest) for your test images, e.g. selective search.
If you want to evaluate a batch of images you can follow the description in the tutorial to generate the test mapping file and the ROI coordinates (see test.txt and test.rois.txt in the corresponding proc sub folder). If you want to evaluate a single you would need to pass the image and the candidate ROI coordinates as inputs to cntk eval, similar to this example:
# compute model output
arguments = {loaded_model.arguments[0]: [hwc_format]}
output = loaded_model.eval(arguments)
For FastRCNN you need to first run your custom image through Selective Search algorithm to generate ROIs (regions of interest) and then feed it to your model with sth like this:
output = frcn_eval.eval({image_input: image_file, roi_proposals: roi_proposals})
You can find more details here: https://github.com/Microsoft/CNTK/tree/release/latest/Examples/Image/Detection/FastRCNN
Anyway FastRCNN is not the most efficient way to do it because of usage of Selective Search (which is a real bottleneck here). If you want to improve the performance you can try FasterRCNN as it gets rid of SS algorithm and replaces it with Region Proposal Network which performs much, much better.
If you're interested, you can check my repo on GitHub: https://github.com/karolzak/CNTK-Hotel-pictures-classificator
Related
I am simulating the case "Cavity driven lid" and I try to get all the stream lines with the stream tracer of paraview, but I only get the ones that intersect the reference line, and because of that there are vortices that are not visible. How can I see all the stream-lines in the domain?
Thanks a lot in adavance.
To add a little bit to Mathieu's answer, if you really want streamlines everywhere, then you can create a Stream Tracer With Custom Source (as Mathieu suggested) and set your data to both the Input and the Seed Source. That will create a streamline originating from every point in your dataset, which is pretty much what you asked for.
However, while you can do this, you will probably not be happy with the results. First of all, unless your data is trivially small, this will take a long time to compute and create a large amount of data. Even worse, the result will be so dense that you won't be able to see anything. You will get all those interesting streamlines through vortices, but they will be completely hidden by all the boring streamlines around them.
Thus, you are better off with trying to derive a data set that contains seed points that are likely to trace a stream through the vortices that you are interested in. One thing you might want to try is to compute the vorticity of your vector field (Gradient Of Unstructured Data Set when turning on advanced option Compute Vorticity), find the magnitude of that (Calculator), and then use the Threshold filter to pull out the cells with large vorticity. Then use that as your Seed Source.
Another (probably better) option if your data is 2D or you can extract an interesting surface along the flow of your data is to use the Surface LIC plugin. Details can be found at https://www.paraview.org/Wiki/ParaView/Line_Integral_Convolution.
You have to choose a representative source for your streamline.
You could use a "Sphere Source", so in the StreamTracer properties.
If that fails, you can use a StreamTracerWithCustomSource and use your own source that you will have to create yourself first.
I thought this should be a simple task, I just can't find the way to do it:
I am using 'imregister' (MATLAB) to register two medical X-ray images.
To ensure I get the best registration outcome as possible, I use some image processing techniques such as contrast enhancement, blackening of objects that are different between images and even cropping.
The outcome of this seems to be quite satisfying.
Now, I want to perform the exact same registaration on the original images, so that I can display the two ORIGINAL images automatically in alignment.
I think that an output parameter such as tform serves this purpose of performing a certain registration on any two images, but unfortunately 'imregister' does not provide such a parameter, as far as I know.
It does provide as an output the spatial referencing object R_reg which might be the answer, but I still haven't figured out how to use it to re-preform the registration.
I should mention that since I am dealing with medical X-ray images on which non of the feature-detecting algorithms seem to work well enough to perform registration, I can only use intensity-based (as opposed to feature-based) registration, and therefore am using 'imregister'.
Does anyone know how I can accomplish this?
Thanks!
Noga
So to make an answer out of my comment, there are 2 things you can do depending on the Matlab release you are using:
Option 1: R2013a and earlier
I suggest modifying the built-in imregister function by forcing tform to be an output and save that function under another name.
For example:
function [movingReg,Rreg,tform] = imregister2(varargin)
save that, add it to your path and you're good to go. If you type edit imregister you will notice that the 1st line calls imregtform to get the geometric transformation required, while the last line calls imwarp, to apply that geometric transformation. Which leads us to Option 2.
Option 2: R2013b and later
Well in that case you can directly use imregtform to get the tform object and then use imwarpto apply it. Easy isn't it?
Hope that makes things clearer!
I am using Caffe to extract features with matlab wrapper.I have 5011 images as test data set.I chopped all the layers after 'relu7' in 'deploy.prototxt'. I found out if you take the same image as input of matcaffe_demo.m and matcaffe_batch.m, you will get the different 4096-dim features.
Could someone tell me why?
what is the differences between you extract features from all these images one by one with matcaffe_demo.m and extract features by listing all these images with matcaffe_batch.m?
You can find the answer to this question at caffe github.
Basically, matcaffe_demo is used for classification and it averages results of 10 crops of the input image, while matcaffe_bathc uses only a single input.
Moreover, note that these m-files are no longer available in recent caffe versions.
Im using the Gaussian Mixture Model to estimate loglikelihood function(the parameters are estimated by the EM algorithm)Im using Matlab...my data is of the size:17991402*1...17991402 data points of one dimension:
When I run gmdistribution.fit(X,2) I get the desired output
But when I run gmdistribution.fit(X,k) for k>2....the code crashes and I get the error"OUT OF MEMORY"..I have also tried an open source code which again gives me the same problem.Can someone help me out here?..Im basically looking for a code which will allow me to use different number of components on such a large dataset.
Thanks!!!
Is it possible for you to decrease the iteration time? The default is 100.
OPTIONS = statset('MaxIter',50,'Display','final','TolFun',1e-6)
gmdistribution.fit(X,3,OPTIONS)
Or you may consider under-sampling the original data.
A general solution to out of memory problem is described in this document.
I've asked this before, but I feel I wasn't clear enough so I'll try again.
I am running a network simulation, and I have several hundreds output files. Each file holds the simulation's test result for different parameters.
There are 5 different parameters and 16 different tests for each simulation. I need a method to store all this information (and again, there's a lot of it) in Matlab with the purpose of plotting graphs using a script. suppose the script input is parameter_1 and test_2, so I get a graph where parameter_1 is the X axis and test_2 is the Y axis.
My problem is that I'm not quite familier to Matlab, and I need to be directed so it doesn't take me forever (I'm short on time).
How do I store this information in Matlab? I was thinking of two options:
Each output file is imported separately to a different variable (matrix)
All output files are merged to one output file and imprted together. In the resulted matrix each line is a different output file, and each column is a different test. Problem is, I don't know how to store the simulation parameters
Edit: maybe I can use a dataset?
So, I would appreciate any suggestion of how to store the information, and what functions might help me fetch the only the data I need.
If you're still looking to give matlab a try with this problem, you can iterate through all the files and import them one by one. You can create a list of the contents of a folder with the function
ls(name)
and you can import data like this:
A = importdata(filename)
if your data is in txt files, you should consider this Prev Q
A good strategy to avoid cluttering your workspace is to import them all into a single matrix. SO if you have a matrix called VAR, then VAR{1,1}.{1,1} could be where you put your test results and VAR{1,1}.{2,1} could be where you put your simulation parameters of the first file. I think that is simpler than making a data structure. Just make sure you uniformly place the information in the same indexes of the arrays. You could also organize your VAR row v col by parameter vs test.
This is more along the lines of your first suggestion
Each output file is imported separately to a different variable
(matrix)
Your second suggestion seems unnecessary since you can just iterate through your files.
You can use the command save to store your data.
It is very convenient, and can store as much data as your hard disk can bear.
The documentation is there:
http://www.mathworks.fr/help/techdoc/ref/save.html
Describe the format of text files. Because if it has a systematic format then you can use dlmread or similar commands in matlab and read the text file in a matrix. From there, you can plot easily. If you try to do it in excel, it will be much slower than reading from a text file. If speed is an issue for you, I suggest that you don't go for Excel.