Questions tagged [convolutional-neural-networks]

For questions about convolutional neural networks, also known as CNN or ConvNet.

Filter by
Sorted by
Tagged with
1
vote
1answer
17 views

When should we use CNN instead of common NN?

Is CNN only applicable to time-series data or image data? When should we use CNN instead of common NN?
0
votes
2answers
21 views

Is it possible to apply 2D convolution to 1D data?

Suppose, I have a 1D dataset with 6 features. Can I apply a 2D convolutional neural net to this dataset?
1
vote
0answers
9 views

Continue teaching pre-trained network without forgetting previous data set

I have a rather interesting problem here; I work in the field of image classification for quality assurance. For this I have a dataset of about 1 million images, which I have used to train different ...
0
votes
0answers
23 views

What does it mean by "low-level" and "high-level" in features generated by CNN?

Across the literature, the terms "high-level" and "low-level" are generally used as an adjective to the features generated by the convolution neural network. Should I understand ...
0
votes
0answers
25 views
0
votes
0answers
23 views

How does bipartite matching work in DETR?

I was going through the DETR paper to understand this end-to-end detection transformer used for object detection, and I came across this bipartite matching thing. I searched a little bit, but I was ...
0
votes
1answer
13 views

Validation accuracy less than training accuracy (with no sigh of overtraining)

I am working with a deep CNN with over 100k sample data. I divided it up into 75% training, 12.5% validation and 12.5% for testing. As I train my network, the training accuracy approaches near 100% ...
0
votes
0answers
32 views

How does Chebyshev approximation of spectral convolution work?

I was reading the following paper: here. In it, it talks about spectral graph convolutions and says: We consider spectral convolutions on graphs defined as the multiplication of a signal $x \in R^N$ (...
0
votes
0answers
25 views

Is it normal that we get different AUC results after running with various seeds?

We are working on optimizing a CNN made for binary image classification (by that I mean to classify each image to group A or group B). It is based on InceptionV3, using PyTorch. We saw that choosing ...
0
votes
1answer
59 views

How do I prepare my data for a CNN to be applied to a geophysical-related problem?

I am currently doing research work on an inversion of geophysical data using Machine Learning. I have come across some research work where a Convolutional Neural Network (CNN) has been used ...
1
vote
0answers
36 views

Is having near-duplicates in a training dataset a bad thing?

I am making a labeled dataset of images from web streams for a CNN classification. Pictures from the same stream are quite similar as far as background, but slightly different as far as the main ...
1
vote
1answer
19 views

How to embed game grid state with walls as an input to neural network

I've read most of the posts on here regarding this subject, however most of them deal with gameboards where there are two different categories of single pieces on a board without walls etc. My game ...
0
votes
0answers
16 views

Dealing with images of multivariate time series

Assuming we have the following input multivariate series: number_of_samples, number_of_timestamps, number_of_features Upon conversion to images using any of the ...
0
votes
0answers
13 views

Preprocessing images for test and validation datasets for training a convolutional neural network (CLAHE)?

I'm training a convolutional neural network for image classification,and i want to preprocess the images, for example with the CLAHE method. I'm not sure if this preprocessing has to be used on the ...
0
votes
1answer
27 views

How to divide a segmented image into classes instances?

Is there a method/algorithm to generate instances of objects from image that was segmented by the use of any image segmentation models? For example, I have an image with one class and it was segmented ...
0
votes
0answers
24 views

Machine Learning Algorithm for OCR on full pages of text

I would like to build an OCR application. In. particular, I want my algorithm to scan entire pages of text in a specific niche language. I was therefore wondering if there are some algorithms that ...
0
votes
1answer
40 views

How do CNNs handle inputs of different sizes and shapes?

I am new to deep learning so feel free to correct me where I am wrong. Imagine this scenario where we have a 7 * 7 input. We want to slide a 3 * 3 filter with a stride of 3 and padding of zero over ...
1
vote
1answer
48 views

Why do some techniques use random augmentations during convolution processes

While going over PyTorch image augmentations, https://pytorch.org/vision/stable/transforms.html, I see that some augmentations can be applied with a certain probability. What is the purpose of ...
0
votes
0answers
13 views

Is it possible to identify which feature maps were generated from a particular image after convolutional operation

Let's say I have a video that contains 3 grayscale sequential frames having a combined shape of (3, 24, 24). After inputting these frames together into a CNN, multiple feature maps will be generated ...
1
vote
1answer
24 views

How does a VGG-based Style-Loss incorporate color information?

I've recently been reading a lot about style transfer, its applications and implications. I understand what the Gram matrix is and does. I can program it. But one thing that has been boggling me is: ...
0
votes
0answers
17 views

Which Neural Network Topology to choose, are Transformers suitable?

I have a regression problem and I am not quite sure which architecture to choose. I never worked with transformers before, but I generally understand how they work and I think they might be suitable. ...
0
votes
1answer
83 views

What is the difference between a vision transformer and image based relational learning

I am trying to figure out the difference between the architecture used in this and this paper. It looks like both used multi-headed self-attention and therefore should be the same in principle.
0
votes
1answer
9 views

What does a value of -1.000 mean in MS COCO Metrics for Object Detection

I am training some Object-Detection-Models from the TensorFlow Object Detection API and got from the evaluation with MS COCO metrics the following results for Average Precision: IoU = 0.5;0.9 maxDets =...
1
vote
2answers
17 views

How can equivariance to translation be a benefit of a CNN?

I just learnt about the properties of equivariance and invariance to translation and other transformations. Being invariant to translation is clearly an advantage, as even if the input gets shifted, ...
0
votes
0answers
30 views

LSTM and CNN - feature engineering and order for time series classification

My questions are related to multivariate time series classification, hence it may differ from forecasting problems. I can have either variable (entire history of the series) or fixed time steps (...
0
votes
1answer
55 views

Why the partial derivative is $0$ when $F_{ij}^l < 0$?. Math behind style transfer

I am currently in the process of reading and understanding the process of style transfer. I came across this equation in the research paper which went like - For context, here is the paragraph - ...
1
vote
0answers
32 views

What would be the advantage of making channel dimension first in TensorFlow Keras implementation?

I was reproducing the findings of a research article in which I discovered that they had switched the Channel dimension from last to first. To clarify this concept, I went through A Gentle ...
2
votes
1answer
34 views

Given an input of shape $(3, 32, 32)$, which is convolved with a $(3 \times 3)$ kernel, how do I calculate the FLOPS?

I have an input tensor of shape $\mathbf{(3, 32, 32)}$ consisting of 3 channels, 16 rows, and 16 columns. I want to convolve the input tensor using $\mathbf{(3 \times 3)}$ kernel/filter. How can I ...
1
vote
0answers
22 views

How to pass variable length data as feature to a neural network?

I am working on building a model to classify the type of touch the user makes(Long Press, Left Swipe, Right swipe and so on). I have data with features that characterise the user's touch, like ...
0
votes
0answers
12 views

What is the significance behind having small kernel sizes over having one large kernel size that covers the entire input in a CNN?

I have hardly ever seen anyone cover the entire input image with a filter of the same dimensions. I was wondering why that is the case, and if the performance in say, an image detection application ...
0
votes
1answer
14 views

Can we change bias and control the output of neural network?

I have read the use of Targeted Adversarial Attacks for making the model perform better. But can we change the bias of the neural networks and control the outcome of the network rather than changing ...
0
votes
2answers
54 views

Why do we lose detail of an image as we go deeper into a ConvNet?

I was reading this research paper titled 'Image Style Transfer using Convolutional Neural Networks' which as the title suggests was based on Neural Style Transfer. I came across this line which didn't ...
1
vote
0answers
15 views

Non-determinism with mixed precision?

Currently, we're trying to improve failure analysis capability when using neural nets. One thing we want to resolve is output variation between batched runs and non-batched runs. For example, we wrote ...
0
votes
0answers
20 views

How to improve detection of wide objects?

I am working on a project where part of it is to detect PV module arrays, I trained few object detection models through TensorFlow Object Detection API and the problem I got is that the trained models ...
0
votes
1answer
253 views

Are the reports on Stanford website are credible(authentic) enough to study? [closed]

I found a bunch of reports of Stanford students available in their website. The following is the link http://cs231n.stanford.edu/reports/ I am aware that materials from Stanford are credible. But, I ...
0
votes
0answers
8 views

Why do we transform feature vectors in attention modules for CNNs

If we have a set of feature maps with dimensions [B, C, H, W] (batch, channel, height, width), why do we transform our feature maps before we calculate their affinity/correlation in attention ...
0
votes
1answer
38 views

Attention mechanism: Why apply multiple different transformations to obtain query, key, value

I have two questions about the structure of attention modules: Since I work with imagery I will be talking about using convolutions on feature maps in order to obtain attention maps. If we have a set ...
1
vote
1answer
49 views

Why do we add 1 in the formula to calculate the shape of the output of the convolution?

In the formula to calculate output shape of tensor after convolution operation $$ W_2 = (W_1-F+2P)/S + 1, $$ where: $W_2$ is the output shape of the tensor $W_1$ is the input shape $F$ is the filter ...
2
votes
0answers
26 views

Is there a systematic way of conducting deep learning experiments?

I have been working on a computer vision problem with the use of cnns, but quite frustratingly I'm often in the situation of not knowing what to do to improve my results. It seems to me that most of ...
0
votes
1answer
31 views

Is a convolutional layer capable of converting, for example, a binary image into an RGBA image?

I am asking this question for a better understanding of the concept of channels in images. I am aware that a convolutional layer generates feature maps from a given image. We can adjust the size of ...
0
votes
0answers
12 views

Deep NN architecture for predicting a matrix from a matrix and list of floats

I am trying to predict a matrix (size RxC) based on an input matrix (size RxC) and a list of floats ...
1
vote
1answer
20 views

Is reconciling shape discrepancies the only purpose of padding?

Padding is a technique used in some of the domains of artificial intelligence. Data is generally available in different shapes. But in order to pass the data as input to a model in deep learning, the ...
0
votes
0answers
13 views

Feeding the output back to input in 3D CNN model

I am currently designing a Model which takes Input 3D Grid and Model Output at $t-1$. The model figure is described below I have two thoughts in training the model for above situation. Feed output $...
0
votes
0answers
19 views

How Tesla and other companies use outputs from neural networks to drive the car?

Here is the short description of Tesla Autopilot AI: https://www.tesla.com/autopilotAI And here are some videos about how Tesla uses neural networks: Andrej Karpathy - AI for Full-Self Driving at ...
0
votes
1answer
46 views

Is it possible to use deep learning to generate a 2D image from a few numerical values?

Is it possible to train a DL model that will generate a full resolution 2D image based on few numbers describing this image and what type of model or architecture would that be? What I want to ...
0
votes
0answers
15 views

Scrabble-MuZero: combine observation planes of different shape

I'm working on an implementation of Scrabble with MuZero. The board state is represented by a matrix with shape $15 \times15 \times 27$ ($26$ letters $+ 1$ wildcard, value $0/1$) and the rack state $...
1
vote
0answers
29 views

Is there any animation that illustrates the "fold" and "unfold" operations of convolutional layers?

There are fourteen convolution layers in PyTorch. Among them six are related to convolution, another six are related to transposed convolution. The remaining two are fold and unfold operations. The ...
1
vote
0answers
26 views

Is there any gain by lazy initialization of weights, biases and number of input channels for a convolution operation?

The basic layers for performing convolution operation in PyTorch are ...
0
votes
0answers
17 views

Prune Neural Networks layers for f% sparsity - TensorFlow2

I am using TensorFlow 2.5 and Python3.8 where I have a simple TF2 CNN having one conv layer and an output layer for binary classification as follows: ...
0
votes
0answers
6 views

The ratio between number of units in multi-input model

I have the model that accepts two inputs: Image from camera Speed of the car I can create some CNN layers to process the image input and some MLP layers to process other type of data (for example ...

1
2 3 4 5
21