7

There are 2 problems you might face. 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. Fully-convolutional implies that it doesn'...


5

There are various dataset available such as Pascal VOC dataset: You can perform all your task with these. size of the dataset is as follows ADE20K Semantic Segmentation Dataset: you can perform only segmentation here COCO dataset: This is rich dataset but a size larger then 5 GB so you can try downloading using google colab in your drive and then make ...


5

The difference between the validation and test set in my opinion should be explained in this way: the validation set is meant to be used multiple times. the test set is meant to be used only once. I think that the misunderstanding here arise because machine learning is mostly taught focusing only on a specific part of a large pipeline, which is the model ...


3

Yes, you can weight the loss function for each example, so that instead of your cost function being $$J = \sum_i \mathcal{L}(y_i, \hat{y}_i)$$ It will be $$J = \sum_i w_i\mathcal{L}(y_i, \hat{y}_i)$$ Where $i$ iterates over your data set, $\mathcal{L}$ is the loss function you are using, $y_i$ is ground truth for each example and $\hat{y}_i$ is ...


3

Of course, it's possible to define a problem where there is no relationship between input $x$ and output $y$. In general, if the mutual information between $x$ and $y$ is zero (i.e. $x$ and $y$ are statistically independent) then the best prediction you can do is independent of $x$. The task of machine learning is to learn a distribution $q(y|x)$ that is as ...


3

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 ...


3

Your data set would be what is called "unbalanced' and this can lead to problems in developing an accurate classifier. The best thing to do (which you might not be able to do) is to find more images for those classes with a smaller number of images. Another alternative is to synthetically produce more images. One way to do that is to use the Keras ...


3

The sentences coming from the same document, author, etc., are unlikely to be independent, that is, the occurrence of a sentence $s_i$ in a certain document $d$ is likely correlated with the occurrence of another sentence $s_j$. If they are not independent, they can also not be independent and identically distributed (which is a stronger condition). The same ...


3

In computer science, if you say "A is a proxy for B", then it means that "A replaces B" (temporarily or not), or that "A is used as an intermediary for B". The term "proxy" usually refers to a server, i.e. there are the so-called proxy servers, which intuitively do the same thing (i.e. they are used as intermediaries). ...


3

Yes it should be possible. You may have a bug in your code, or the wrong hyperparameters. Training ResNet-50 will take a long time. Try training on other sets of images and see what accuracy you get to check if your approach is correct. Or, try loading a pretrained model, and training from that.


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

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

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

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

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

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

In this paper: Unsupervised Machine Translation Using Monolingual Corpora Only the authors proposed a novel method. Intuitively it is an autoencoder, but the Start Of Sentence token is set to be the language type. One other advanced method is to use the pre-training model. In this paper: Cross-lingual Language Model Pretraining researchers proposed an ...


2

If you used your five $X_{test}$ sets multiple times (to measure the average AUC) to decide on the best set of hyperparameters (i.e. optimizer, learning rate, batch size, dropout, activation) then yes, you successfully conducted hyper-parameter optimization. However, the AUC you received for the best set of hyperparameters found (by manual tuning) is not ...


2

Assuming you pass through the entire validation dataset, this can't be due to shuffling since you still compute the loss/accuracy over the entire dataset, so order does not really matter here. It is more likely that you have a significantly smaller or less representative validation dataset, e.g., distribution of the validation dataset can be skewed towards ...


2

Simply stated, you use your validation set to regularize your model for unseen data. Test data is completely unseen data, on which you evaluate your model. Various validation strategies are used to improve your model to perform for unseen data. So strategies like k-fold cross-validation are used. Also, the validation set helps you in tuning your ...


2

A typical clustering algorithm is k-means (and not k-NN, i.e. k-nearest neighbours, which is primarily used for classification). There are other clustering algorithms, such as hierarchical clustering algorithms. sklearn provides functions that implement k-means (and an example), hierarchical clustering algorithms, and other clustering algorithms. To assess ...


2

One problem with clustering algorithms is that they will typically find you a solution, ie they will split your data set into clusters, but it will find you a structure even if there isn't one. Your data looks like it could consist of about 5 to 7 clusters, but it could equally well just be 2 or only 1. What you need to do after the clustering is to assess ...


1

You can find the dataset in the following links: Pomegranate Disease Detection Using Image Processing fruits 360 datasets


1

If you want to evaluate on real thermal image dataset, you can use this one. Thermal Image dataset is mAP a relevant metric when I want to show result to a client ? (e.g a client doesn't understand if I tell him "my model has a mAP=0.7") Mean Average Precision is the relevant metric but it's more technical. You can start explaining with False Positives ...


1

NDDS is a UE4 plugin from NVIDIA to empower computer vision researchers to export high -quality synthetic images with metadata. NDDS supports images, segmentation, depth, object pose, bounding box, keypoints, and custom stencils. In addition to the expo rter, the plugin includes different components for generating highly randomized images. This randomization ...


1

Do you have to upload the images as image files (PNG, etc.)? If you can also upload the images in data format, then Kaggle might be a good solution. You can upload datasets there and share them publicly for data scientists to explore them, you can even add a sample notebook. I have done this with some image data myself which I used for a GAN. If the data ...


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 ...


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