Wolfram Mathematica

« first day (2484 days earlier) ← previous day next day → last day (2017 days later) »

4:08 AM

Maybe can try FCN, which only need to train a Classifier. I'm waiting for some newer API from mxnet to do target detection.

It is still very difficult to implement some complex loss functions with WLNet.

1 hour later…

C. E.

5:20 AM

I played with this sample problem this summer. The thing about that problem is that I can generate an arbitrary amount of training data, but still I couldn't make it work. Possibly because I used too small networks or something, but I'm not sure... the current problem is similar, only the card generally takes up a larger area of the image generally.

(The answers suggesting Yolo etc. are not relevant because Yolo doesn't find the center of the card, it just finds the center of the bounding box.)

@GalAster I should try that. It's similar though to the networks that I've tried, only that I put a couple of fully connected layers at the end.

C. E.

5:52 AM

One possibility may be to run Yolo, extract the bounding box, and then run a key point detection network on the extracted image. In that scenario, all cards will more or less take up the entire image. That's more similar to facial key point detection.

4 hours later…

Carl Lange

9:42 AM

@C.E. Do you have some code to generate training data for the cards thing? Just wondering.

C. E.

10:11 AM

@CarlLange I'll upload it when I get home.

3 hours later…

Carl Lange

12:44 PM

I wish I could like the entity framework but I find it so slow... If I want to get the next 30 rises of a satellite it takes multiple minutes! :(

anyone have any idea how I could make this go, like, a lot faster?

Map[SatelliteData[Entity["Satellite", "42969"],
   EntityProperty["Satellite", "RiseTime", {
     "Date" -> #,
     "Location" -> Here
     }]] &, whens]

with whens = DatePlus[Now, Quantity[#, "Hours"]] & /@ Range[1, 300, 1]

(I know I said 30 above but I really meant... all of them

)

3 hours later…

KraZug

3:28 PM

I have a list, and I want to go through and partition them into subgroups based on applying a function to the list, by applying the function to increasingly large ranges until the value reaches a cutoff. I.e. if I have list={1,2,2,1,3,1,1,0,1,2,1} and I want to split it into subgroups whose Total is <=3, f[list, Total[#]<=3] = {{1,2},{2,1},{3},{1,1,0,1},{2,1}}. I'm guessing there is a function f for that, but don't know what it is.

Jason B.

4:00 PM

@KraZug - I can't say if there's a built in function for that, you can use Split though:

In[39]:= splitByTotal[list_, max_] := Module[{runningTotal = 0},
Split[list,
If[(runningTotal += #1) >= max, runningTotal = 0; False, True] &]
]
splitByTotal[list, 3]

Out[40]= {{1, 2}, {2, 1}, {3}, {1, 1, 0, 1}, {2, 1}}

Szabolcs

4:25 PM

New IGraph/M release available. Please upgrade! It's easy with the upgrade script.

@Richard and anyone else who might be using it. ↑

C. E.

5:15 PM

@CarlLange The speedup is only modest, but in almost all cases this is what you want to do:

whens = DatePlus[Now, Quantity[#, "Hours"]] & /@ Range[1, 300, 1];
properties = EntityProperty["Satellite", "RiseTime", {"Date" -> #, "Location" -> Here}] & /@ whens;
values = SatelliteData[Entity["Satellite", "42969"], properties];

Getting all the data in one request is often much faster than sending several hundred requests, because behind the scenes they are made as one request to the server instead of many.

@CarlLange @GalAster I've posted a link to the code for generating the training data here: chat.stackexchange.com/rooms/85401/…

Carl Lange

5:34 PM

@C.E. Thanks a lot, I couldn't figure out how to do it this way :)

PlatoManiac

6:23 PM

I am getting some message like this in Linux (Ubuntu 18.04) `Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/pratip/.local/lib/python3.6/site-packages/wolframclient/evaluation/kernel/kernelsession.py", line 143, in __init__
'Kernel not found at %s.' % kernel)
` when I run the start a session in python 3.6 `session = WolframLanguageSession('/usr/local/Wolfram/Mathematica/11.3')` @ArnoudBuzing

Sorry my mistake the path was wrong.

4 hours later…