Kaggle: TrackML Particle Tracking Challenge - machine-learning

I'm new to ML and Kaggle. I was going through the solution of a Kaggle Challenge.
Challenge: https://www.kaggle.com/c/trackml-particle-identification
Solution: https://www.kaggle.com/outrunner/trackml-2-solution-example
While going through the code, I noticed that the author has used only train_1 file (not train_2, 3, …).
I know there is some strategy involved behind using only the train_1 file. Can someone, please, explain why is it so? Also, what are the use of blacklist_training.zip, train_sample.zip, and detectors.zip files?

I'm one of the organiser of the challenge. train_1 2 3 .. files are all equivalent. Outrunner has probably seen there was no improvement using more data.
train_sample.zip is a small dataset equivalent to train_1 2 3... provided for convenience.
blacklist_training.zip is a list of particles to be ignored due to a small bug in the simulator (not very important).
detectors.zip is the list of the geometrical surfaces where the x y z measurements are made.
David

Related

Is the chrome devtools doc wrong about the Dominator concept in memory analysis?

https://developers.google.cn/web/tools/chrome-devtools/memory-problems/memory-101#dominators
This is the first time I'm exposed to this concept. After some study, I can understand it now. But when I head back to the doc, what's documented looks pretty confusing to me.
What the heck is "Dominator objects are comprised of a tree structure because each object has exactly one dominator. "? From my understanding, an object can possibly have multiple dominators.
Besides, the description to the diagram below says Node 2 dominates nodes 3, 4, and 6. But isn't Node 2 dominating all nodes but node 1?
I just need someone in the know to confirm this because I can't imagine such awful information in the google doc.

How to make your own custom image dataset?

As I am working on my project that is to detect FOD (Foreign Object Debirs) that is found on the runway. FOD include anything like nuts, bolts, screws, locking wires, plastic debris, stones etc. that has the potential to cause damage to the aircraft. Now I have searched on the Internet to find any image dataset but no dataset is available related to FOD. Now my question is kindly guide me that how can I make my own dataset of images that can then be used for training purpose.
Kindly guide me in making image dataset for both classification and detection purposes. And also the data pre-processing that will be required. Thanks and waiting for the reply!
Although the question is a bit vague regarding your requirements and the specs of your machine, I'll try to answer it. You'll need object detection to do your task. There are many models available which you can use like Yolo, SSD, etc..
To create your own dataset, you can follow these steps:
Take lots of images of your objects of interest in various conditions, viewpoints and backgrounds. (Around 2000 per class should be good enough).
Now annotate (or mark) where your object is in the image. If you're using Yolo, make use of Yolo-mark for annotating. There should be other similar tools for SSD and other models.
Now you can begin training.
These steps should get you started or at least point you in the right direction.
You can build your own dataset with this code. I wrote it, and it works correctly.
You need to import the libraries and add your DATADIR.
if __name__ == "__main__":
for category in CATEGORIES:
path = os.path.join(DATADIR, category)
class_num = CATEGORIES.index(category)
for img in os.listdir(path):
try:
img_array = cv2.imread(os.path.join(path,img))
new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))
training_data.append([new_array, class_num])
except Exception as e:
pass
for features, label in training_data:
x_train.append(features)
y_train.append(label)
#create pikle
pickle_out = open("x_train.pickle", "wb")
pickle.dump(x_train, pickle_out)
pickle_out.close()
pickle_out = open("y_train.pickle", "wb")
pickle.dump(y_train, pickle_out)
pickle_out.close()
In case if you're starting completely from scratch, you can use "Dataset Directory", available on Play store. The App helps you in creating custom datasets using your mobile. You'll have to sign in to your Google drive such that your dataset is stored in Drive rather on your mobile. Additionally, It also contains Labelling the entity for classification and Regression predictive models.
Currently, the App supports Binary Image Classification and Image Regression.
Hope this Helped!
Download Link :
https://play.google.com/store/apps/details?id=com.applaud.datasetdirectory

Tiny YOLOv3 (Darknet) training "too quickly" and produces different output

I am pretty new to YOLO/Darknet and am walking in circles with the solutions. I have looked at the Github and Stackexchange fora pages corresponding with similar issues, but none seems to directly address this output issue (i.e. where the region IOU line is missing). Here is my output (training/testing):
Here is my directory structure:
Other details:
I am using the AlexeyAB fork.
6 classes in total (following this convention of annotating occluded and truncated items, so two "items" with three classes each)
I'm using 200+ training images (definitely too few, but I don't know if this is the root cause of my troubles).
There is no predictions.png, just predictions.jpg. However, I don't think this should be an issue.
I followed this tutorial.
Any help is very much appreciated; thank you in advance!
If it finish too soon on training, try adding -clear 1at the end of your training command.
EDIT:
This is the correct answer (ergo why I accepted it), but lacks an explanation. The "-clear 1" flag is, according to this answer, clears past stats.

Using R to map seedling locations using set reference points

I'm looking for some guidance on the approach I should take to mapping some points with R.
Earlier this year I went off to a forest to map the spatial distribution of some seedlings. I created a grid—every two meters I set down a flag with a tagname, and what I did is I would measure the distance from a flag to a seedling, as well as the angle using a military compass. I chose this method in hopes of getting better accuracy (GPS Garmins prove useless for this sort of task under canopy cover).
I am really new to spatial distribution work altogether, so I was hoping someone could provide guidance on what R packages I should use.
First step is to create a grid with my reference points (the flags). Second step is to tell R to use a reference point and my directions to mark the location of a seedling. From there come other things, such as cluster analysis.
The largest R package for analysing point pattern data like yours is spatstat which has a very detailed documentation and an accompanying book.
For more specific help you would need to upload (part of) your data so we can see how it is organised and how you should read it in and convert to standard x,y coordinates.
Full disclosure: I'm a co-author of both the package and the book.

Zener Diode - What constitutes "Similar?"

I have very little experience with ECE in general and I am delving into using an Arduino for some small hobby type projects.
I was following an online guide, and the person who wrote says that I need:
"2 - 1N5227 or similar 3.6V biased zener diodes"
I have read up a bit on Zener Diodes and now understand what they do and what their purpose is. I am not able to tell what he means by similar in this context though. I purchased a Diode Kit that includes 4 types of Zener Diodes. They all have different part numbers and voltages.
The 4 I have are:
1N751 5.1V
1N4733 5.1V
1N4735 6.2V
1N4742 12V
Would any of those be usable in this context or should I order the specific model he states?
The guide being referenced is this, if it is helpful: http://www.instructables.com/id/RC-Transmitter-to-USB-Gamepad-Using-Arduino/
I really appreciate the time and assistance with this, this is a fun area to learn in!
In electronics and other engineering areas, similar refers to the property that stands out (in this case the voltage), in your case refers to looking for another zener diode whose voltage is similar to the example. As I see none of those diodes replaces the example.
Zener diodes has two parameters you need to match in the selection of a replacement (independently the manufacturer):
The Zener voltage (Vz) and the diode power.
For your application you will need a Zener diode of 3.6 V, and usually with 1/4 W to 1/2 W (depending the application power you will need) it will be enough.
You need also to calculate the limiting resistor for the Zener diode.
I recommend you to read the book of Albert Paul Malvino or similar to better understand.
Regards.

Resources