In the tensorboard utility that comes with tensorflow 1.4 there is a DISTRIBUTIONS tab to the left of the HISTOGRAMS tab. When I look at a distribution, there is a light and dark color. Example:
What do the light and dark colors mean? I'm pretty sure dark is the more common values (say, the middle n-th percentiles of the distribution), but I can't find docs on it.
Ah, found documentation:
Each line on the chart represents a percentile in the distribution
over the data: for example, the bottom line shows how the minimum
value has changed over time, and the line in the middle shows how the
median has changed. Reading from top to bottom, the lines have the
following meaning: [maximum, 93%, 84%, 69%, 50%, 31%, 16%, 7%,
minimum]
These percentiles can also be viewed as standard deviation boundaries
on a normal distribution: [maximum, μ+1.5σ, μ+σ, μ+0.5σ, μ, μ-0.5σ,
μ-σ, μ-1.5σ, minimum] so that the colored regions, read from inside to
outside, have widths [σ, 2σ, 3σ] respectively.
Related
I have a matrix with the next fields:
It’s very hard to navigate; when expanding, the folder paths can be confused with names…
How can I set the background color for the first 5 columns to yellow? (which correspond do the background color).
(Ideally it should look something like):
(My goal is to then add a legend that says ie: Background color Yellow=Path, white=user, access).
Most of the conditional formatting I have seen it plays with numbers, but unfortunately all my data is just text.
I want to plot two class of points with python with different colors , but when I plot them with scatter those points which overlap other ones obscure them.
What I mean is I want to show both of the points (e.g green & purple) in one fixed point.
My Code :
plt.scatter(range(1,len(tp_labels)+1),[x[1] for x in tp_labels ],color = 'purple')
plt.scatter(range(1,len(tp_labels)+1),[x[2] for x in tp_labels ],color = 'green')
As you can see the green overwrites the purple on overlapped points.
I would appreciate your solutions.
I think what you need is to tinker with your alpha settings in order to develop the amount of transparency that best suits your particular circumstances. In matplotlib/pyplot the alpha setting determines the transparency of the item you are plotting. Its values can range as follows (0.0 transparent through 1.0 opaque).
Check out the documentation here and you'll see that you have the option to adjust the alpha setting for almost anything in matplotlib/pyplot up to and including the legends and even the plot background. This should solve your issue regarding subsequent plots obliterating earlier ones.
When using TGraphErrors, the error bars appear as crosses, in the absence of significant X errors and many, many data points (such as MCA with 16k bins or so) I'd like to be able to remove the single points and single error bars and graph the error as a shaded region bounding the curve from above and below.
But I'm still a rank beginner at using ROOT, and I cannot figure out how to leverage TGraphErrors to do what I want. Will I need to instead use a TMultiGraph instead (and calculate the above and below bounding curves) and if so how can I control the shading region?
Something like the below would be along the lines of what I'm looking for. Source
Take a look at the TGraphPainter documentation which gives a few examples. One way is to draw the TGRaphErrors using option 4:
A smoothed filled area is drawn through the end points of the vertical error bars.
You will probably find that to get the final plot to look as you want, you have to draw the same graph multiple times - once to get the shaded region, then again on top to get the central curve.
This blog post gives a working example. It's written in PyROOT, but can be easily adapted to C++.
Each red circle in this map is a point but due to the density of them, there isn't enough space to show the text labels for all of them. So I want to filter them down to just show those which can show a text label.
How can I do this? marker-spacing seemed to be promising but makes no difference. I see no "marker-min-distance" as there is with "text-min-distance".
Basically there's no point in showing a marker at all if it can't be identified with text. This is for a non-interactive offline map.
There is marker-spacing.
If you want to draw only labelled markers, use shields instead (answered here).
I would like to know if among the OpenCV filter functions, is there a particular one that is suited to remove horizontal/vertical banding noise in an image? Like, for salt and pepper noise, Gaussian blur works best. Or, is the process of removing banding noise a combination of different filters?
Did try several filters already like bilateral, gaussian, median and blur(homogenous), but the vertical banding lines don't seem to disappear or significantly reduce, or sometimes the resulting image is just so smoothed. I'd prefer the image to be retained, only that the noise is removed.
I am interested to do the removal of noise in OpenCV, c++ in particular. Any basic steps, concepts or tutorial would be great. Thanks
The sample images are here which shows obvious marks of vertical bands of noise. These images are outputs of a scanner by the way.
https://drive.google.com/file/d/0B1aXcXzD_OADMkNuNnJxNGw2NTA/edit?usp=sharing
https://drive.google.com/file/d/0B1aXcXzD_OADNkFBbGgxU20yMjg/edit?usp=sharing
I would do it like this:
1.find your lines
for example search for repetitive bumps/edges on first derivation by x or y;
then select only those which are in average period place
and neighbouring lines/rows has also this bump near the same place
2.remove pixels of selected lines
just take color before and after bump
and interpolate between them (avg color for example)
also in some case you can substract constant color from all pixels of the line
depends on the color mixing mechanism which created those lines
You can reduce vertical or horizontal noise by adjusting the kernel size using simple blur operation
Fir example for your vertical noised image you could use
blur(src,dst,Size(11,1));
Note that here the kernel size in vertical direction is higher value compared to horizontal.
See the image before and after filtering
Similarly for horizontal just use reverse kernel size like
blur(src,dst,Size(1,11));
See the result