I'm trying to use apple's Accelerate Framework to setup FFT, windowing, overlapping and downsampling with input taken from the device's microphone. I've been looking all over for some sample code/application on how to use it, but I didn't quite figure out how to implement something like this in an actual project. Could you help point me in the right direction? Thanks
UPDATE
Here is the code I've managed to put together so far from various sources, including some other questions answered here. What it's missing is a downsampling function and the overlapping. In Apple's documentation, I found the following function vDSP_zrdesamp for desampling but i'm having trouble implementing it.
The real problem is trying to put this in an actual project. I've tried modifying this github project but I didn't manage to fit it in, so any help would be more than welcome. The actual FFT (which I need to modify) takes places in the RIOInterface class, in the audio callback function.
Please note that the project I mention on github does not belong to me, but it does not have a licence that forbids me to modify it for my own purposes. Also, this project is for testing only until I reach a more stable algorithm.
Related
Are there any tools to monitor network's training in PyTorch? Like tensorboard in tensorflow.
PyTorch 1.1.0 supports TensorBoard natively with torch.utils.tensorboard. The API is very similar to tensorboardX. See the documentation for more details.
I am using tensorboardX. It supports most (if not all) of the features of TensorBoard. I am using the Scalar, Images, Distributions, Histograms and Text. I haven't tried the rest, like audio and graph, but the repo also contains examples for those use cases. The installation can be done easily with pip. It's all explained in the README file of the repo.
There are also other github repos which implement a wrapper for PyTorch (and other languages/frameworks) to tensorboard. As far as I know they support fewer functionalities. But have a look at:
Crayon
Tensorboard-Logger
I have asked this question before in the forums. Tensorboard seems very convenient for Tensorflow and it is also made part of the library/framework itself. However, PyTorch wouldn't take the same approach. But there is a library called visdom here that is released by Facebook, that helps you log the training information. This gives you the flexibility of logging information the way you want. While this means a lot of flexibility, it also means you need to write some extra code to make things work.
Following up on blckbird's answer, I'm also a big fan of Tensorboard-PyTorch. However I also found that its API is relatively low level and I was writing a lot of similar code over and over to do the logging. So (shameless plug) I've written a small package on top of it to automate monitoring network training experiments with minimal code. Hopefully someone else finds it helpful. pytorch-monitor
Minetorch helps me a lot at the past 2 Kaggle competitions. I think it's ready for others to use. It has built-in tensorboard or matplotlib supported. And many other features which make the work easy, includes:
Logger
Tensorboard supported
Matplotlib (to generate png to file)
Auto resume training
Auto best model saving
Hook points for customize
...
It's still in developing so any issues or PRs are very welcomed : )
I have streaming continuous data that I need to filter by frequency. I have high-level knowledge of FFT and frequency filtering, but no real practical knowledge.
After searching for a suitable library to aid me, I came across Math.NET's Neodym Signal Processing Library (https://mathnetneodym.codeplex.com/releases/view/91769)
I downloaded it, upgraded it to VS2010 and used the SignalGenerator class to generate various sine wave of various frequencies. It worked great.
Now, I need to know how to filter dynamic data. This StackOverflow question seems to come the closest to mine, and is a good start:
Filtering continuous data, how to get rid of transients?
There is a .chm file in the downloaded project, but it seems to just be the API documentation. I need some high-level help just pointing me in the right direction to use the library.
Can anybody provide a good resource to refer to so I can use this library for my purpose?
Thank you!
John
UPDATE
I'm pretty sure I use the OnlineFilter.CreateBandpass static function with the mode ImpulseResponse.Infinite... but I'll post whatever I find out.
I have a MP3 file and need to constantly detect and show Hz value of this playing MP3 file. A bit of googling shows that I have 2 opportunities: use FFT or use Apple Accelerate framework. Unfortunately I haven't found any easy to use sample of neither. All samples, like AurioTouch etc, need tons of code to get simple number for sample buffer. Is there any easy example for pitch detection for iOS?
For example I've found https://github.com/clindsey/pkmFFT, but it's missing some files that its' author has removed. Anything working like that?
I'm afraid not. Working with sound is generally hard, and Core Audio makes no exception. Now to the matter at hand.
FFT is an algorithm for transforming input from time domain to frequency domain. Is not necessarily linked with sound processing, you can use it for other things other than sound as well.
Accelerate is an Apple provided framework, which among many other things offer an FFT implementation. So, you actually don't have two options there, just one and its implementation.
Now, depending on what you want to do(e.g. if you favour speed over accuracy, robustness over simplicity etc) and the type of waveform you have(simple, complex, human speech, music), FFT may be not enough on its own or not even the right choice for your task. There are other options, auto-correlation, zero-crossing, cepstral analysis, maximum likelihood to mention some. But none are trivial, except for zero-crossing, which also gives you the poorest results and will fail to work with complex waveforms.
Here is a good place to start:
http://blog.bjornroche.com/2012/07/frequency-detection-using-fft-aka-pitch.html
There are also other question on SO.
However, as indicated by other answers, this is not something that can just be "magically" done. Even if you license code from someone (eg, iZotope, and z-plane both make excellent code for doing what you want to do), you still need to understand what's going on to get data in and out of their libraries.
If you need fast pitch detection go with http://www.schmittmachine.com/dywapitchtrack.html
You'll find a IOS sample code inside.
If you need FFT you should use Apple Accelerate framework.
Hope this help
I am using an Arduino to control a car and I want to make it autonomous by using a webcam to see the object I want and make the car move to this location. I need several things:
MATLAB code
Interface between MATLAB and Arduino
How do I connect between them (software, not hardware)
I need any tutorial to learn or any instructions to make my project. I see many people have done this before, but unfortunately they did not mention how to start these kind of projects.
This question is fairly broad, so I apologize in advance for my somewhat general response.
The easiest way to interface a webcam with MATLAB is to make use of the Image Acquisition Toolbox. This link provides documentation detailing how to do this.
There is a good chance that you'll also want to make use of the Image Processing toolbox in MATLAB to be able to process the acquired images to determine where to go. See this doc. Though, after you've determined more specifically how you plan to process these images, there are probably numerous algorithms that you could find online that would not explicitly require this toolbox.
As far as interfacing with Arduino is concerned, there is a support package from the MathWorks that allows you to interface MATLAB code and Simulink models with Arduino. See this link
The only other general suggestion that I have is to consider using Simulink for this project rather than MATLAB. I feel that the model based approach of Simulink is a much better fit when designing control systems.
I hope that this helps you get things started.
For my computer vision class, I'm going to be doing a project where I extract information about a hallway based on an image of that hallway. In particular, the lines of the hallway which extend toward a vanishing point will be of interest. My question is whether I should use Matlab, OpenCV, or something else to implement this.
I don't have a ton of time for this project. This fact makes Matlab seem like a good option since it seems you can usually get things up and running quickly there. On the other hand, I hope to take what I do for this class project and extend it out further for research once the class is complete. This makes OpenCV seem better as (from what I've read) it's much more efficient. It's possible another choice would be to implement it in Matlab for the project than port that code to an OpenCV form later. It should be noted that I have plenty of experience with C/C++, but only a little in both Matlab and OpenCV.
At the moment, I'm leaning toward just using OpenCV from the start. However, I would like the opinion of someone who's had a bit more experience here than myself. If you'd recommend something over both OpenCV and Matlab, please say so. Also, if you have any tips on what packages or toolkits might be useful for such a project, they would be greatly appreciated.
Any suggestions? Thanks for your time!
Using which one it is easier for you to write a piece of code to read an image file and display it?
If you know C++ very well, then it should be easy to debug the code. Since you say you have little experience with Matlab, if you make a small mistake in the code debugging can take a long time.
So I suggest break down the problem into:
read image and display it, this is very easy in both
detect edges using a simple/classic method, this is super easy in both, display the result and visually check it's correctly done
use a robust line fitting method, the RANSAC and Hough transform methods are probably what you're going to use, OpenCV makes using the easier than you can guess, Matlab also has built in functions to detect lines using the Hough transform, and gives you the start/end points of each segment. But if you're finding a vanishing point, you shouldn't need those.
The decision is yours, this is not a very difficult problem, can find loads of help on the web. Good luck with the project, and please let us know how it goes.