New answers tagged

0

I think you might have misunderstood 2 concepts here: CNNs and Object Detection. Object Detection is an AI approach to solve problems where you are interested in both the location and the classification of key elements in the image. On the other hand Image Classification is another approach where you are interested in classify the whole image with a tag. ...


1

Try removing the dropout before the prediction layer. I couldn't find the paper or article I read about this (will update the post once I find it), just found a Cross Validated post which does not add much information. As you are If you are lowering the learning rate, you should also lower the batch size accordingly. As for Batch Normalization layers, they ...


2

This one is a bit crazy: pool1 = nn.AvgPool3d(kernel_size = (361, 1, 1), stride= 1) because it averages large numbers of the features at once. Very little information about individual features will remain after doing that. The most obvious one you have not tried is this: pool3 = nn.AvgPool3d(kernel_size = (3, 1, 1), stride= (3, 1, 1)) which includes all ...


0

The ideal hyperparameters is usually dependent on your dataset and will differ on a case by case basis. Go for trial and error to determine the hyperparameters that works best for you. Few research papers similar to your use case is listed below. CNN transfer learning for visual guitar chord classification A Study of Left Fingering Detection Using CNN for ...


1

What is the No Information Rate (NIR)? I.e. what are the percentages of positive and negative labels? Have you looked at the predictions of your model? If it's all 0's or all 1's then it probably learned nothing, other than predicting the majority class. When it comes to architectural choices and hyperparameters, especially if you start working with NNs, ...


1

The dimensionality used to discuss convolutional layers in CNNs is based on the dimensionality of the input without considering channels. 1D CNNs might process raw audio sources (mono or stereo), text sequences, IR spectrometry from a single sample point 2D CNNs can process photographic images (regardless of colour/depth etc information), audio spectrograms,...


1

Kernel dimensionality and presence of filters decides the dimension of convolution operator. N Dimensional Convolutions have N dimensional kernels. For example, from Keras Documentation on 2 Dimensional Convolutions: kernel_size: An integer or tuple/list of 2 integers, specifying the height and width of the 2D convolution window. Can be a single integer to ...


1

I am not really a fan of the One vs All approach. From my experience it is never convenient to transform a multi-class classification problem with, say, $N$ possible classes to a bunch of binary classification problems. Reason #1 The number of binary classifiers you need to train scales linearly with the number of classes. Hence, you can easily find ...


0

You can do whatever the heck you want. Of course you will have to design the data flow through the network so that it can make whatever inferences you intend it to make. The first channel (containing the 4 traces) will then have a set of filter weights, shared among the 4 traces. The second channel (containing the 1 trace) will have a completely different ...


1

Paper 1- If I'm understanding the paper correctly, the "Measurements " just represents a collection of auxiliary information. It's not necessarily a single speed measurement, but any auxiliary information, so perhaps gas level, engine temperature, etc. I think them choosing to show a speedometer as a measurement might not be the best choice ...


1

I would expect the dense layers to be able to detect certain speed ranges. This neuron activates for 0-10, this one for 10-20, this one for 20-30, this one for 20-50, this one for 47.6-89.2... Of course a later layer could also do that, but it looks like there aren't many layers after this one.


1

I am not sure if there really are contradicting opinions on this matter. CNNs, RNNs, LSTMs all have specific types of data they are good at predicting. Depth and width, or in general the size of the neural network mostly depends on the size of your dataset. You don't want to build a too large network that will overfit the available data, which can usually be ...


1

I think there's a crucial point missed in the question, touched by jros answer but without further elaboration. If you train a model on domain A: single lightning condition and test it on domain B: two lightning condition then you're not evaluating generalization but transfer learning capabilities. Or to phrase it differently you're evaluating how close ...


0

Generalization In machine learning, generalization describes a model's ability to properly correct its algorithms to predict new data from the same distribution as the data used to train the model. By providing additional training for your model (on data with varying lighting conditions), you are correct that you would be increasing the capabilities of your ...


Top 50 recent answers are included