6

Non-Euclidian geometry can be generally boiled down to the phrase "the shortest path between 2 points isn't necessarily a straight line". Or, put in a way that lends itself very much to machine learning, "things that are similar to each other are not necessarily close if one uses eucidian distance as a metric" (aka the triangle inequality doesn't hold)...


3

I do not know a specific tool that meets all the mentioned requirements. However, a long time ago, I had to do a very similar task of labeling tons of images into 10 classes. This is how I did this: Used a very basic clustering tool to cluster images into clusters (I set the number of clusters larger than 10 as I new some classes have very different ...


3

There are a few tools that you can use to annotate (or label) data. For example, labelme or Labelbox. Have a look at this question for more alternatives.


3

So I am assuming that you are trying to detect a lego brick from the image. One idea is that you can use transfer learning. Leveraging a pre-trained machine learning model is called transfer learning. The underlying idea behind transfer learning is that one takes a well-trained model from one dataset or domain, and applies it to a new one. François Chollet ...


3

I will give a more thorough answer. There are 2 problems you might face. 1) Your neural net (in this case convolutional neural net) cannot physically accept images of different resolutions. This is usually the case if one has Fully-Connected layers, however if the network is Fully-Convolutional then it should be able to accept images of any dimension. ...


2

I think you'll enjoy this work from Apple on improving the realism of synthetic images. Essentially what you need to do is generate a synthetic image then have your GAN modify the synthetic image so that a 1) a discriminator thinks it is real while also 2) not changing the gross structure of the image very much (so the traffic sign doesn't move) - yes, this ...


2

I believe that the idea is to have a similar ratio of fraud/"normal transaction" as to the ones that bank encounter on real life. If you balance it you will probably have a lot of false positive once you apply your solution to real world's data and, if that may be fine for you to play with, it's not what a bank would like as they can't block too much of the ...


2

Look at Google's Open Image Dataset @ https://storage.googleapis.com/openimages/web/index.html They provide image-level labels, object bounding boxes, object segmentation masks, and visual relationships. Here is the link for the traffic signs dataset.


2

You can take a look at traffic data for example if you follow link1, link2 you can find 3 publicly available traffic datasets which are already preprocessed. You cold also look at air quality datasets offered by the government link3


2

Before jumping to modeling, there are a few tasks a data scientist (or ML/AI practitioner) must do: Ideation (or hypothesizing): Before applying any modeling approach, we need to ask the right questions. We must clearly mention our assumptions and declare how we want to measure the effectiveness of the pipeline. Note that, some tools/algorithms might not ...


2

This should be possible given the fact that ANNs have the ability to do the feature engineering and feature selection tasks by themselves. This means that given a lesser number of input parameters, the model will be able to generate and select additional features by itself. You will obviously not be able to understand or model these features manually. The ...


2

It depends on what is your ultimate goal. If your goal is to simply classify the object in the image, having more complex output won't help. Simpler output representation yields better result. If your goal is to detect the bounding box, output the bounding box. There is no need for a more complex output feature. If you use a segmentation method for bounding ...


2

Perhaps you can check this dataset out: http://www.aiskyeye.com/ The VisDrone2019 dataset is collected by the AISKYEYE team at Lab of Machine Learning and Data Mining , Tianjin University, China. The benchmark dataset consists of 288 video clips formed by 261,908 frames and 10,209 static images, captured by various drone-mounted cameras, covering ...


2

I am assuming the question you are asking is how to prevent over-fitting on the maximum accuracy. Your graph does show that your model over-fits. There is a couple of different methods to prevent over-fitting from happening. You can specify training to stop after a certain amount of epochs. In your case it seems to be 2 or 3 epochs. Take care as a new ...


2

This could be possible, providing you have the right dataset to train it on. The volume of a cup consist of width, height and depth. You can probably detect all three of those given the bounding box or the pixels of the cup. However detecting the dimensions of an object require a reference object, like a penny or your finger and you have to specify the ...


2

It is explained in this CrossValidated post. Top1 accuracy means the best guess (class with highest probability) is the correct result 58.9% of the time, while top5 accuracy means the correct result is in the top 5 best guesses (5 classes with highest probabilities) 87.7% of the time.


2

Decision Tree learners, on their own, are not a good way to deal with imbalanced data. The most commonly used algorithms, by default, make no attempt to address this problem. If you look carefully at the three sources you post, you will find that they actually all agree on this point. Two of the sources actually propose methods of addressing this ...


2

You should use both classes together. Let's say you use the method you proposed. Then they will be contradicting each other as one teaches the network to recognize people, not objects and the other teaches the network to recognizes objects not person. There is no need for seperation of the two classes, unless you are making two seperate classifier. Hope I ...


2

You can't label things you don't know. The goal of labeling is to label the things you want the classifier to learn so that when you run it in inference mode you can discover what is in your data (new data that you didn't use for training, validating, or testing). It is not a good idea to label small objects like the 'blue water' unless it is important to ...


2

Is your question about storing, writing, or reading/processing huge data? I'm not an expert in this topic, but I know a couple of possible ways to handle huge datasets: If the data is too big to be fully uploaded to RAM, you can iterate over it in Pandas. You can find a brief explanation in the article Why and How to Use Pandas with Large Data, section 1. ...


1

I think what you are actually talking about is semantic segmentation (where you label pixels individually). There is a difference in theses tasks like Classification, Detection or Semantic Segmentation. Classification refers to the task of giving a (usually) single label to the whole image, e.g. cat. But as you already noticed this does not nececerraly ...


1

Answering my own question here. Looked at the Open Image Dataset by Google @ https://storage.googleapis.com/openimages/web/index.html They provide image-level labels, object bounding boxes, object segmentation masks, and visual relationships.


1

You can use append function: final = df1.append(df2, ignore_index=True) To set the last column as labels, you set them as so by: labels = np.array(final["will_buy"]) So, when calling the fit method on the model you build, you set labels = labels.


1

They don't have acces to the original training or test dataset. Machine learning environments are build on the premise of a benign environment. The models are trained on real data (real inputs). When someone sends a made up input (fake input) it is very easy to fool the model. This is used for example in image recognition. Imagine a fotograph of a panda. ...


1

is your data stored in raw ASCII text, like a CSV file? Perhaps you can speed up data loading and use less memory by using another data format. A good example is a binary format like GRIB, NetCDF, or HDF. There are many command line tools that you can use to transform one data format into another that do not require the entire dataset to be loaded into ...


1

Data scaling or normalization is a process of making model data in a standard format so that the training is improved, accurate, and faster. So you just have to scale the data once. Doesn't matter what scaler you are using. Just make sure to initialize the scaler with the training data and then use the same parameters to scale the test data. The z-score ...


1

For such time-series data that has a significant amount of periodicity, I would recommend converting data to the frequency domain and performing various spectral analysis methods as @firion has already mentioned. For example, you could perform Fourier Analysis and study the individual components and identify patterns there. Also, it generally not ...


1

I have found a script that does what i need: https://github.com/leblancfg/autocrop


1

In order to accurately input location data into a machine learning model it really depends on what your goal is and what type of algorithm you are working with. If you are working with a strictly numerical algorithm and your data seems to be spread far apart, it might be easier to convert your country-state-city location to a longitude, latitude feature ...


1

Affluence could encompass several parameters: Income; Wealth (property ownership); Life expectancy; Access to services such as education and health; Access to clean natural resources; Low levels of criminality. Property prices in each locality might be easy to obtain from real estate agent sources Ratings for schools or medical facilities in each area might ...


Only top voted, non community-wiki answers of a minimum length are eligible