Frames per second meaning for object detection - machine-learning

How do you interpret "frames per second" when it comes to computer vision models?
If my model can analyze each test image in .50 seconds, does that mean it's 2 frames per second since it can analyze 2 images in one second?

Yes, you are right. At the end it only depends on where you use it. Online/offline, video or photo. The construct of frames per seconds processing speed (FPS) is a way to express how fast the method is. Often you can bump it to the term "real time" which is a way to express that the method can process a video sequence "online" with the asumption of the video having a frame rate of 25 (FPS). The term "real time" is often disliked, because in and of itself it does not state anything.

Related

How would I break down a signals sound pressure level by frequency

I've been given some digitized sound recordings and asked to plot the sound pressure level per Hz.
The signal is sampled at 40KHz and the units for the y axis are simply volts.
I've been asked to produce a graph of the SPL as dB/Hz vs Hz.
EDIT: The input units are voltage vs time.
Does this make sense? I though SPL was a time domain measure?
If it does make sense how would I go about producing this graph? Apply the dB formula (20 * log10(x) IIRC) and do an FFT on that or...?
What you're describing is a Power Spectral Density. Matlab, for example, has a pwelch function that does literally what you're asking for. To scale to dBSPL/Hz, simply apply 10*log10([psd]) where psd is the output of pwelch. Let me know if you need help with the function inputs.
If you're working with a different framework, let me know which, 100% sure they'll have a version of this function, possibly with a different output format in which case the scaling might be different.

Python: time stretch wave files - comparison between three methods

I'm doing some data augmentation on a speech dataset, and I want to stretch/squeeze each audio file in the time domain.
I found the following three ways to do that, but I'm not sure which one is the best or more optimized way:
dimension = int(len(signal) * speed)
res = librosa.effects.time_stretch(signal, speed)
res = cv2.resize(signal, (1, dimension)).squeeze()
res = skimage.transform.resize(signal, (dimension, 1)).squeeze()
However, I found that librosa.effects.time_stretch adds unwanted echo (or something like that) to the signal.
So, my question is: What are the main differences between these three ways? And is there any better way to do that?
librosa.effects.time_stretch(signal, speed) (docs)
In essence, this approach transforms the signal using stft (short time Fourier transform), stretches it using a phase vocoder and uses the inverse stft to reconstruct the time domain signal. Typically, when doing it this way, one introduces a little bit of "phasiness", i.e. a metallic clang, because the phase cannot be reconstructed 100%. That's probably what you've identified as "echo."
Note that while this approach effectively stretches audio in the time domain (i.e., the input is in the time domain as well as the output), the work is actually being done in the frequency domain.
cv2.resize(signal, (1, dimension)).squeeze() (docs)
All this approach does is interpolating the given signal using bilinear interpolation. This approach is suitable for images, but strikes me as unsuitable for audio signals. Have you listened to the result? Does it sound at all like the original signal only faster/slower? I would assume not only the tempo changes, but also the frequency and perhaps other effects.
skimage.transform.resize(signal, (dimension, 1)).squeeze() (docs)
Again, this is meant for images, not sound. Additionally to the interpolation (spline interpolation with the order 1 by default), this function also does anti-aliasing for images. Note that this has nothing to do with avoiding audio aliasing effects (Nyqist/Aliasing), therefore you should probably turn that off by passing anti_aliasing=False. Again, I would assume that the results may not be exactly what you want (changing frequencies, other artifacts).
What to do?
IMO, you have several options.
If what you feed into your ML algorithms ends up being something like a Mel spectrogram, you could simply treat it as image and stretch it using the skimage or opencv approach. Frequency ranges would be preserved. I have successfully used this kind of approach in this music tempo estimation paper.
Use a better time_stretch library, e.g. rubberband. librosa is great, but its current time scale modification (TSM) algorithm is not state of the art. For a review of TSM algorithms, see for example this article.
Ignore the fact that the frequency changes and simply add 0 samples on a regular basis to the signal or drop samples on a regular basis from the signal (much like your image interpolation does). If you don't stretch too far it may still work for data augmentation purposes. After all the word content is not changed, if the audio content has higher or lower frequencies.
Resample the signal to another sampling frequency, e.g. 44100 Hz -> 43000 Hz or 44100 Hz -> 46000 Hz using a library like resampy and then pretend that it's still 44100 Hz. This still change the frequencies, but at least you get the benefit that resampy does proper filtering of the result so that you avoid the aforementioned aliasing, which otherwise occurs.

Throughput vs. Latency Confusion

According To This Article about Throughput and Latency H
"When You Go To Buy a Water Pipe, There Are Two Completely Independent Parameters That You Look At: The Diameter of the Pipe and Its Length"
But I Think These Two Parameters Are Related. Throughput Is Measured As Per Unit Time, So A Long Latency Will Affect Throughput, Say, If The Droplet Is Fast, More Of Them Will Pass The Pipe In One Second,
Can Any One Help Me Understand This?
EDIT:
the confusion is originated from counting queuing time as part of latency which we should not. Once a request is handled, the latency is independent of throughput.
Let me give you another anology...Think of a car travelling on a single lane road from location A to location B..time taken by that car to travel from A to B is your latency...and the number of cars travelling at an interval, maintaining the latency is your throughput.
The factors that affect here is your medium of travel ie by road and no of lanes on the road.
You're thinking about frequency. Say you have a window into the water pipe at some given point, and you send water droplets at some constant interval (say 1 droplet ever second). You count how often you see a single droplet pass by, and take the inverse (1/seconds). So if you count 1 second of elapsed time between droplets being observed, then you have a frequency of 1Hz.
Now say that you keep this frequency constant (1Hz), but you elongate the pipe. You send one droplet down and count how much time elapses before it reaches the end of the pipe. So say it takes 2 seconds for a single drop to travel from the beginning to the end of the pipe, then you have a latency of 2 seconds.
Now say that you widen the diameter of the pipe, and now you are able to send 2 droplets with a frequency of 1Hz. At the end of the pipe you will count 2 droplets coming out every second. So your throughput will be 2 droplets per second.
Here is my bit in a language which I can understand
When you go to buy a water pipe, there are two completely independent parameters that you look at: the diameter of the pipe and its length. The diameter determines the throughput of the pipe and the length determines the latency, i.e., the time it will take for a water droplet to travel across the pipe. Key point to note is that the length and diameter are independent, thus, so are are latency and throughput of a communication channel.
More formally, Throughput is defined as the amount of water entering or leaving the pipe every second and latency is the average time required to for a droplet to travel from one end of the pipe to the other.
Let’s do some math:
For simplicity, assume that our pipe is a 4inch x 4inch square and its length is 12inches. Now assume that each water droplet is a 0.1in x 0.1in x 0.1in cube. Thus, in one cross section of the pipe, I will be able to fit 1600 water droplets. Now assume that water droplets travel at a rate of 1 inch/second.
Throughput: Each set of droplets will move into the pipe in 0.1 seconds. Thus, 10 sets will move in 1 second, i.e., 16000 droplets will enter the pipe per second. Note that this is independent of the length of the pipe. Latency: At one inch/second, it will take 12 seconds for droplet A to get from one end of the pipe to the other regardless of pipe’s diameter. Hence the latency will be 12 seconds.

Number Generator wave cycle to graph output

I'm looking to generate a wave form generated by a cycle of numbers that increase and then decrease on a given rate. The frequency can vary between 1 to 40 per minute and the amplitude varies between 100 and 3000. The idea is to form a breathing like pattern for "breaths per minute" (1-40) and an inhaled volume per breath (100-3000).
I'm new here and I can only find random generators. I have looked at NSTimer and UIGraphs from the Ios-Developer Tesla tutorial app.
Could anyone point me in the right direction.
Many Thanks.

Software Phase Locked Loop example code needed

Does anyone know of anywhere I can find actual code examples of Software Phase Locked Loops (SPLLs) ?
I need an SPLL that can track a PSK modulated signal that is somewhere between 1.1 KHz and 1.3 KHz. A Google search brings up plenty of academic papers and patents but nothing usable. Even a trip to the University library that contains a shelf full of books on hardware PLL's there was only a single chapter in one book on SPLLs and that was more theoretical than practical.
Thanks for your time.
Ian
I suppose this is probably too late to help you (what did you end up doing?) but it may help the next guy.
Here's a golfed example of a software phase-locked loop I just wrote in one line of C, which will sing along with you:
main(a,b){for(;;)a+=((b+=16+a/1024)&256?1:-1)*getchar()-a/512,putchar(b);}
I present this tiny golfed version first in order to convince you that software phase-locked loops are actually fairly simple, as software goes, although they can be tricky.
If you feed it 8-bit linear samples on stdin, it will produce 8-bit samples of a sawtooth wave attempting to track one octave higher on stdout. At 8000 samples per second, it tracks frequencies in the neighborhood of 250Hz, just above B below middle C. On Linux you can do this by typing arecord | ./pll | aplay. The low 9 bits of b are the oscillator (what might be a VCO in a hardware implementation), which generates a square wave (the 1 or -1) which gets multiplied by the input waveform (getchar()) to produce the output of the phase detector. That output is then low-pass filtered into a to produce the smoothed phase error signal which is used to adjust the oscillation frequency of b to push a toward 0. The natural frequency of the square wave, when a == 0, is for b to increment by 16 every sample, which increments it by 512 (a full cycle) every 32 samples. 32 samples at 8000 samples per second are 1/250 of a second, which is why the natural frequency is 250Hz.
Then putchar() takes the low 8 bits of b, which make up a sawtooth wave at 500Hz or so, and spews them out as the output audio stream.
There are several things missing from this simple example:
It has no good way to detect lock. If you have silence, noise, or a strong pure 250Hz input tone, a will be roughly zero and b will be oscillating at its default frequency. Depending on your application, you might want to know whether you've found a signal or not! Camenzind's suggestion in chapter 12 of Designing Analog Chips is to feed a second "phase detector" 90° out of phase from the real phase detector; its smoothed output gives you the amplitude of the signal you've theoretically locked onto.
The natural frequency of the oscillator is fixed and does not sweep. The capture range of a PLL, the interval of frequencies within which it will notice an oscillation if it's not currently locked onto one, is pretty narrow; its lock range, over which it will will range in order to follow the signal once it's locked on, is much larger. Because of this, it's common to sweep the PLL's frequency all over the range where you expect to find a signal until you get a lock, and then stop sweeping.
The golfed version above is reduced from a much more readable example of a software phase-locked loop in C that I wrote today, which does do lock detection but does not sweep. It needs about 100 CPU cycles per input sample per PLL on the Atom CPU in my netbook.
I think that if I were in your situation, I would do the following (aside from obvious things like looking for someone who knows more about signal processing than I do, and generating test data). I probably wouldn't filter and downconvert the signal in a front end, since it's at such a low frequency already. Downconverting to a 200Hz-400Hz band hardly seems necessary. I suspect that PSK will bring up some new problems, since if the signal suddenly shifts phase by 90° or more, you lose the phase lock; but I suspect those problems will be easy to resolve, and it's hardly untrodden territory.
This is an interactive design package
for designing digital (i.e. software)
phase locked loops (PLLs). Fill in the
form and press the ``Submit'' button,
and a PLL will be designed for you.
Interactive Digital Phase Locked Loop Design
This will get you started, but you really need to understand the fundamentals of PLL design well enough to build it yourself in order to troubleshoot it later - This is the realm of digital signal processing, and while not black magic it will certainly give you a run for your money during debugging.
-Adam
Have Matlab with Simulink? There are PLL demo files available at Matlab Central here. Matlab's code generation capabilities might get you from there to a PLL written in C.

Resources