Questions tagged [convolutional-neural-networks]

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

Filter by
Sorted by
Tagged with
0
votes
0answers
12 views

How to set loss weight to zero for an output dimension in keras?

Suppose I am training a model to detect facial keypoints that allow occlusions to be present. The input is an image of a face, and the model has to predict the x,y coordinate of both eyes and mouth. ...
1
vote
0answers
19 views

How to implement CNN with variable number of images in tensorflow or keras?

Suppose I have a problem where I want to classify the color of LEDs seen in the image. I can use OpenCV to pinpoint the exact location of these LEDs but I do not know their color for sure because the ...
2
votes
1answer
48 views

Do models train better if the dataset is more specific? (Semantic Segmentation / Bounding Box / Image classification)

I'm working on a project where there is a limited dataset of videos (about 200). We want to train a model that can detect a single class in the videos. That class can be of multiple different types ...
2
votes
1answer
31 views

Is it possible to vectorise a CNN?

I am trying to write a CNN from scratch and am wondering if it possible to vectorise the convolution step. For example, if I had a dataset of 500 RGB images of size 32x32x3, and wanted the first conv ...
2
votes
1answer
15 views

Should I use my redundant feature as an auxiliary output or as another input feature?

For example, given a face image, and you want to predict the gender. You also have age information for each person, should you feed the age information as input or should you use it as auxiliary ...
1
vote
0answers
14 views

CNN multi output scores and evaluation

I am building a CNN with two outputs. I still have to put time in the network itself, but I was trying to get a good evaluation/classification report of the results. My code is the following: ...
0
votes
0answers
4 views

Would models like U-Net be able to segment objects which has label based on its surrounding context?

Suppose that we want to segment a red blob from the image, normally you will have a class for this red blob e.g. 0. And every red blob you detected will have a class of 0. But in my case, I want that ...
1
vote
1answer
14 views

Positioning of batch normalization layer when converting strided convolution to convolution + blurpool

I'm trying to replace the strided convolutions of Keras' MobileNet implementation with the ConvBlurPool operation as defined in the Making Convolutional Networks ...
1
vote
1answer
25 views

Is a VGG-based CNN model sometimes better for image classfication than a modern architecture?

I have an image classification task to solve, but based on quite simple/good terms: There are only two classes (either good or not good) The images always show the same kind of piece (either with or ...
6
votes
1answer
41 views

Are there well-established ways of mixing different inputs (e.g. image and numbers)?

I am interested in the possibility of having extra input along with the main data. For instance, a medical application that would rely mostly on an image: how could one also account for sex, age, etc.?...
2
votes
1answer
43 views

What are the features get from a feature extraction using a CNN?

I've just started to learn CNN and somewhere I have read if I remove the last FCL I will get the features extracted from the input image but... what are those features? Are they numbers? Labels? An ...
1
vote
1answer
52 views

How can I use feature extraction in CNN with image segmentation?

I'm just started to learn about meta learning and CNN and in most paper that I've read they mention to have one CNN to feature extraction. These features will help the another network. I don't know ...
4
votes
1answer
47 views

Calculating Weights for CNN Max Pooling Output

How do i calculate weights for max pooling output? For example if there are 10 inputs, a pooling filter of size and a stride 2, how many weights including bias are required for the max pooling output ...
2
votes
0answers
22 views

Which neural network algorithms can be used to map motion vectors in image processing?

I'm working on finding out the motion vectors of objects in images. The inputs are the images of objects in motion. The outputs of neural network are the object name, direction of object vector and ...
4
votes
2answers
63 views

What are the best algorithms for image segmentation tasks?

I recently started looking for networks that focus on image segmentation tasks related to biomedical applications. I could not miss the publication U-Net: Convolutional Networks for Biomedical Image ...
1
vote
0answers
9 views

Is there any time-varying directed graph dataset?

I am interested in the node classification task for graph data. So far,I've tried it with the Cora dataset, but it is an undirected graph and has word attributes as features. I want to extend this ...
1
vote
1answer
100 views

Neural networks for sports betting

I want to design a neural network that can be used for predicting sports scores for betting, specifically for American football. What I’d like to do is create a kind of profile for each game based on ...
2
votes
1answer
48 views

When and how to use a mix of loss functions for back-propagation?

I am trying to understand the best loss function to be used with a convolutional neural network. I came to know that we can mix two loss functions. Can any body share in what case was it done and how?
1
vote
2answers
80 views

What are the standard problems for CNNs and LSTMs?

What are the standard (or baseline) problems (or at least common ones) for CNNs and LSTMs? As an example, for a feed-forward neural net, a common problem is the XOR problem. Is there a standard ...
0
votes
1answer
78 views

Neural Network to estimate distance

I built a three layer neural network (first is 1D Convolutional and the remaining two are Linear). It takes an input of 5 angles in radians, and outputs two numbers from 0 to 1, which are respectively ...
0
votes
0answers
17 views

Computing layers dimensions for deep learning architectures

I have already a few projects in deep learning under my belt. However, there is one fundamental thing that has come to my mind recently while trying to implement my own architecture. Looking at the ...
3
votes
1answer
60 views

CNN how can i reduce gpu memory usage with large image sizes?

I am trying to train a cnn-lstm model, my sample image sizes are 640x640. I have a GTX 1080 ti 11GB. I am using Keras with tensorflow backend. Here is the model. ...
2
votes
0answers
47 views

CNN clasification model loss stuck at same value

I have CNN model to classify 2 classes. (Yes or No) I use categorical_crossentropy loss and softmax activation at the end. For input I use image with all 3 channels, for output I use One hot encoded ...
0
votes
0answers
59 views

What to do when an image classifier does good for a class but bad for another?

So I wrote a convolutional neural network for a binary image classification. I have around 5300 images for each class which I thought would be enough to at least give me a good accuracy on the ...
3
votes
1answer
44 views

Can a model, retrained on images classified previously by itself, increase its accuracy?

Let's assume I have a CNN model trained to categorize some objects on the images. By using this model I find more categorized images. If I now retrain this model on data set that consists old set and ...
3
votes
1answer
48 views

GPU/TPU acceleration for neural networks with various network topologies

I was thinking about different neural network topologies for some applications. However, I am not sure how this would affect the efficiency of hardware acceleration using GPU/TPU/some other chip. If, ...
0
votes
0answers
14 views

Numbers to image regression

I would like to create a machine learnig framework that could predict the 3D heat distribution of a room(of size 120x120x120) , given multiple parameters(position of the heater, orientation, power of ...
1
vote
0answers
24 views

How to get same accuracy with identical models in Keras and Tensorflow?

As we all know Keras backend uses Tensorflow and so it should give out same kind of results when we provide same parameters, hyper-parameters, weights and biases initialisation at each layer, but ...
4
votes
0answers
35 views

Get the position of an object, out of an image

I have some images with a fixed background and a single object on them which is placed, in each image, at a different position on that background. I want to find a way to extract, in an unsupervised ...
0
votes
0answers
8 views

Looking for the right type of 1D-Convolution that only considers one column/attribute

My input has the shape of n rows (time steps) and m columns (attributes). I want to train a convolutional neural network on it to predict a class. I am currently using 1D-Convolutions. I got a good ...
0
votes
0answers
10 views

How much data is needed to train a deep learning model to detect instance masks?

I am trying to get an idea of how much data is needed to train a deep convolutional neural network to detect instance masks from images. I am interested in both papers that have been written on the ...
1
vote
0answers
68 views

Threshold selection for Siamese network hyper-parameter tuning

I'm interested in modeling a Siamese network for facial verification. I've already written a simple working model that inputs feature vectors generated from two CNNs with shared weights then outputs a ...
3
votes
1answer
23 views

Image classification with an associated matrix

I have a dataset of images with 9 different classes. However, there are different categories with the same type of associated image and only can be differentiated with an associated matrix in my ...
1
vote
1answer
33 views

How well can ConvNET distinguish an object from its class?

ConvNET can easily predict class of an object in an image. My question is, can ConvNET distinguish Pisa Tower from other buildings or Hagia Sophia from other mosquoes easily? If it can, how many ...
0
votes
0answers
71 views

Matterport MRCNN and multiclass classification

I want to create a model which solve a multiclass classification problem. The main concept is: every picture contain only one object the background is very simple all object is coming from the same ...
1
vote
0answers
17 views

Sliding Window Detection

Suppose that we have a labeled training set of $n$ closely cropped images of cars $(x_1, y_1) , \dots, (x_n, y_n)$. We then train a CNN on this. Let's say we have $m$ test images. Then for each of the ...
0
votes
1answer
48 views

Generate credit cards dataset for locating number region

Currently I'm working on a project for scanning credit card and text extraction from cards. So first of all I decided to preprocess my images with some filters like thresholding, dilation and some ...
1
vote
0answers
41 views

Which approaches are best suited for text deblurring?

I want to deblur text images using deep learning. Which approaches are best suited for the task? Any example networks? Is unsupervised network the best approach? GAN or cycle GAN for these purposes? ...
2
votes
0answers
21 views

Confidence Maps and Non-Linearity

I am currently trying to improve a CNN architecture that was proposed for generating depth images. The architecture was originally proposed for autonomous driving and it looks like following : The ...
1
vote
0answers
23 views

Reference request: one-hot encoding outperforming random orthogonal encoding

I experimented with a CNN operating on texts encoded as sequences of character vectors, where characters are encoded as one-hot vectors in one embedding and as random unit length pairwise orthogonal ...
3
votes
1answer
53 views

Is it useful to eliminate the less relevant filters from a trained CNN?

Imagine I have a tensorflow CNN model with good accuracy but maybe too many filters: Is there a way to determine which filters have more impact in output? I think it should be possible. At least, if ...
0
votes
1answer
67 views

Should I use single or double view for gender recognition?

My project requires gender recognition of people shown on the given images, with more than one person per image. However, these people can be positioned in frontal or side view(passing by ...
1
vote
1answer
34 views

What does an oscillating validation error curve represent?

I have been training my CNN for a bit now and, while both the training loss and the training error curves are going down during training, both my validation loss and my validations error curves are ...
0
votes
0answers
21 views

Training, validation loss and accuracy yolov3?

This is a version of Yolo V3 implemented in PyTorch – YOLOv3 in PyTorch I am trying to use transfer learning to train this yolov3 implementation following the directions given in this post. This is ...
1
vote
2answers
31 views

How does one create a non-classifying CNN in order to gain information from images?

How do I program a neural network such that, when an image is inputted, the output is a numerical value that is not the probability of the image being a certain class? In other words, a CNN that doesn'...
1
vote
1answer
28 views

What should load_mask() return if an image doesn't have any objects? (Mask RCNN)

I want to use Mask RCNN to do image segmentation. I need to override the load_mask function for the dataset class. I know this function should return mask tensors and class ids of objects in an image. ...
2
votes
1answer
45 views

Understanding the intuition behind Content Loss (Neural Style Transfer)

I'm trying to understand the intuition behind how the Content Loss is calculated in a Neural Style Transfer. I'm reading from an articles: https://medium.com/mlreview/making-ai-art-with-style-transfer-...
3
votes
1answer
111 views

What are the differences between Bytenet and Wavenet?

I recently read Bytenet and Wavenet and I was curious why the first model is not as popular as the second. From my understanding, Bytenet can be seen as a seq2seq model where the encoder and the ...
2
votes
1answer
33 views

Transfer learning to train only for a new class while not affecting the predictions of the other class

I am basically interested in vehicle on the road. YoloV3 pytorch is giving a decent result. So my interested Vehicles Car ...
1
vote
0answers
20 views

Loss reduction, but constant performance with CNN

I made a CNN with a reasonable loss curve, but the performance of the model does not improve. I have tried making the model larger, I am using three convolutional layers with batch norms. Thanks for ...