Questions tagged [convolutional-neural-networks]
For questions about convolutional neural networks, also known as CNN or ConvNet.
580
questions
3
votes
1answer
21 views
Why do CNN's sometimes make highly confident mistakes, and how can one combat this problem?
I trained a simple CNN on the MNIST database of handwritten digits to 99% accuracy. I'm feeding in a bunch of handwritten digits, and non-digits from a document.
I want the CNN to report errors, so I ...
1
vote
1answer
26 views
Param count in last layer high, how can I decrease?
Not sure where to put this... I am trying to create a convolutional architecture for a DQN in keras, and I want to know why my param count is so high for my last layer compared to the rest of the ...
1
vote
1answer
48 views
How many layers exists in my neural network?
I have a neural network model defined as below. How many layers exist there? Not sure which ones to count when we are asked about the number.
...
2
votes
1answer
35 views
What make a CNN suitable for image classification or for semantic segmentation?
I've just started with CNN and there is something that I haven't understood yet:
How do you "ask" a network: "classify me these images" or "do semantic segmentation"?
I think it must be something on ...
1
vote
0answers
14 views
How can we combine different deep learning models?
I know that ensembles can be made by combining sklearn models with a VotingClassifier, but is it possible to combine different deep learning models? Will I have to make something similar to Voting ...
1
vote
0answers
18 views
Efficient implementation of seperable convolution in tensorflow
It seems like the native implementation of separable convolution in tensorflow is not efficient.
https://github.com/tensorflow/tensorflow/issues/12940
Is anyone aware how can we get an efficient ...
1
vote
0answers
4 views
What is generally the best way to combine tabular image metadata with image data in a convolutional neural network?
I have 26 features from tabular data (clinical variables from patients like age gender etc) that I want to add to my cnn which is using xray images from patients. I am using the inception network. ...
2
votes
1answer
30 views
What are examples of approaches to dimensionality reduction of feature vectors?
Given a pre-trained CNN model, I extract feature vector of images in reference and query dataset with several thousands of elements.
I would like to apply some augmentation techniques to reduce the ...
1
vote
1answer
27 views
Where can I upload a large photo database for public access?
I am applying for a grant, and one of the tasks we are seeking funding for is to make a large image database publicly available for users to train artificial intelligence (convolutional neural network)...
4
votes
1answer
60 views
Which deep learning models are suitable for image-to-image mapping?
I am working on a problem in which I need to train a neural network to map one or more input images to one or more output images (1 channel for image). Below I report some examples of input&output....
-1
votes
0answers
26 views
How could one track the feature locations in a convolution neural network?
A major problem with deep learning, according to Hinton, is that operations like max-pooling remove the position information of features with respect to each other.
How one might attempt to track ...
1
vote
0answers
10 views
Scoring feature vector with Support Vector Machine
I am reading the R-CNN paper by Ross Girshick1 et al. (link) and I fail to understand how they do the inference. This is described in the section 2.2.Test-time Detection in the paper. I quote:
At ...
1
vote
1answer
14 views
Best Camera and protocol for embedded real time CNN project
I'm looking to develop a stand-alone real-time outdoor imaging CNN application, and I can't wrap my head around the myriad of camera options and their communication protocols.
The target is a Linux ...
1
vote
0answers
30 views
Reinforcement learning CNN input weakness
I'm trying to train a network to navigate a 48x48 2D grid, and switch pixels from on to off or off to on. The agent receives a small reward if correct, and small punishment if incorrect pixel plotted.
...
1
vote
1answer
50 views
Why everyone is using CNN for image segmentation?
I'm newbie in artificial intelligence.
I have started to research about how to do image segmentation and all the papers that I have found are about CNN. Most of them use the same network, U-NET, but ...
2
votes
0answers
16 views
How many ways are there to perform image segmentation?
I'm new in Artificial Intelligence and I want to do image segmentation.
Searching I have found these ways
Digital image processing (I have read it in this book: Digital Image Processing, 4th edition)...
1
vote
1answer
22 views
When training a CNN, what are the hyperparameters to tune first?
I am training a convolutional neural network for object detection. Apart from the learning rate, what are the other hyperparameters that I should tune? And in what order of importance? Besides, I read ...
1
vote
0answers
16 views
Training dataset for convolutional neural network classification - will images captured on the ground be useful for training aerial imagery?
I am an agronomy graduate student looking to classify crops from weeds using convolutional neural networks (CNNs).
The basic idea that I am wanting to get into involves separating crops from weeds ...
0
votes
1answer
16 views
Set my own kernels to a CNN and don't let it to modify it
I'm newbie in Convolutional Neural Networks and I have discovered (and I hope I'm right) that kernels in convolutional layers are learned while training.
If I have a kernel that it is very good to ...
3
votes
0answers
30 views
What are some ways to quickly evaluate the potential of a given NN architecture?
Main question
Is there some way we can leverage general knowledge of how certain hyperparameters affect performance, to very rapidly get some sort of estimate for how good a given architecture could ...
2
votes
0answers
14 views
Is it normal to see oscillations in tested hyperparameters during bayesian optimisation?
I've been trying out bayesian hyperparameter optimisation (with TPE) on a simple CNN applied to the MNIST handwritten digit dataset. I noticed that over iterations of the optimisation loop, the tested ...
2
votes
0answers
52 views
Suggestion for finding the stable regions in spiral galaxy data?
I am working with a data set that consists of the actual pitch angle (given as PA(Y)) and the pitch angle at each radii (listed from 1 to 217). In the image below, ...
2
votes
1answer
18 views
Semantic Segmentation For Multiple Objects When Trained On Single Object
More of a conceptual question here:
I'm working on semantic segmentation tasks in the medical space using the U-Net. Let's say that I train a U-Net model on medical images with the goal of segmenting ...
1
vote
0answers
11 views
YOLOv3 Synthetic Data Training
Suppose we want to train a model to detect various objects. Let's say we have training data of those objects in various backgrounds along with their bounding boxes. Basically these objects have been ...
1
vote
1answer
61 views
What is a cascaded convolutional neural network?
For a project I am doing, I found the paper Face Alignment in Full Pose Range: A 3D Total Solution.
It is using a cascaded convolutional neural network, but I wasn't able to find the original paper ...
3
votes
0answers
27 views
How can I do hyperparameter optimization for a CNN-LSTM neural network?
I have built a CNN-LSTM neural network with 2 inputs and 2 outputs in Keras. I trained the network with model.fit_generator() (and not ...
4
votes
0answers
29 views
Autoencoder produces repeated artifacts after convergence
As experiment, I have tried using an autoencoder to encode height data from the alps, however the decoded image is very pixellated after training for several hours as show in the image below. This ...
3
votes
1answer
85 views
How to formalize learning in terms of information theory?
Consider the following game on a MNIST dataset:
There are 60000 images.
You can pick any 1000 images and train your Neural Network without access to the rest of images.
Your final result is ...
3
votes
1answer
29 views
How are small scale features represented in an Inverse Graphics Network (autoencoder)?
This post refers to Fig. 1 of a paper by Microsoft on their Deep Convolutional Inverse Graphics Network:
https://www.microsoft.com/en-us/research/wp-content/uploads/2016/11/kwkt_nips2015.pdf
Having ...
2
votes
2answers
52 views
Calculation of FPS on object detection task
How to calculate mean speed in FPS for an object detection model like YOLOv3 or YOLOv3-Tiny? Different object detection models are often presented on charts like this:
I am using the DarkNet ...
2
votes
1answer
63 views
The reasoning behind the number of filters in the convolution layer
Let's assume an extreme case in which the kernel of the convolution layer takes only values 0 or 1. To capture all possible patterns in input of $C$ number of channels, we need $2^{C*K_H*K_W}$ filters,...
2
votes
0answers
14 views
Which CNN hyper-parameters are most sensitive to centered versus off centered data?
Which hyper-parameters of a convolutional neural network are likely to be the most sensitive to depending on whether the training (and test and inference) data involves only accurately centered images ...
3
votes
1answer
55 views
How to create a fully connected(matrix) layer with vector input
I am trying to replace last fully connected layer of size 4096/2048 with a matrix of size 100x300 with previous fc layer output of 2048.
I've tried
2D convolution - to map from 2048 --> 100x300 (...
2
votes
0answers
32 views
How to understand my CNN's training results?
I created a multi-label classification CNN to classify chest X-ray images into zero or more possible lung diseases. I've been doing some configuration tests on it and analyzing its results and I'm ...
0
votes
0answers
19 views
Is it possible to combine multiple SVMs that were trained on sublayers of a CNN into one combined SVM?
I have created a CNN for use on the MNIST dataset for now (so I have 10 classes). I have trained SVMs on the sublayers of this trained CNN and wish to combine them into a combined SVM as to give a ...
0
votes
1answer
30 views
not sure if fine-tuned network is finely-tuned
I am practicing with Resnet50 fine tuning for binary classification task, here is my code snippet.
...
1
vote
0answers
20 views
Hinton's Capsule network 16 dimensions
As you may know, Hinton's Capsule Network has been around for about 2 years now. https://arxiv.org/abs/1710.09829
Much ado has been made about how the Capsules output a vector (magnitude = ...
2
votes
1answer
34 views
Accuracy scores in a Deep Learning project
I'm using three pre-trained deep learning models to detect vehicles and count from an image data set. The vehicles belong to one of these classes ['car', 'truck', 'motorcycle', 'bus']. So, for a ...
1
vote
1answer
54 views
How many parameters are being optimised over in a simple CNN?
Okay so here's my CNN (simple example from a tutorial) along with some arithmetic to get the total number of free parameters.
We've got a dataset of 28*28 grayscale image (MNIST).
First layer is a ...
1
vote
1answer
31 views
How to explain peak in training history of a convolutional neural network?
I am training a simple convolutional neural network to recognize two types of 1024-point frequency spectra (FFT). This is the model I'm using:
...
1
vote
0answers
16 views
Flattened vector observation or convolutional neural network input?
This is more of a general question of how to model/preprocess 'visual' state-observations to an Agent in Reinforcement Learning that I'll illustrate with an example.
Say you have a reinforcement ...
0
votes
2answers
42 views
How can I convert the probability score between 0 to 1 to another format?
I have trained a multi-class CNN model using fastai. The model splits out probabilites for each of the three classes, which, of course, sum up to 1. The class with highest probability becomes the ...
0
votes
2answers
57 views
What is a front-end and back-end in the context of convolutional neural networks?
The title is mainly it really.
I googled that phrase or variations of it and couldn't find a decent result.
0
votes
0answers
14 views
Optimizer effects on neural network with two outputs
I'm confused about the following issue. Let assume that we have a neural network that takes one input and two outputs. I try to visualize my model like as follows:
...
1
vote
0answers
25 views
Imposing contraints on sequence of image classifications
Are there example implementations of networks that apply constraints across sequences of image classifications where class labels are ordinal numbers? For example, to cause the output of a CNN to ...
0
votes
0answers
14 views
Affine Transformations and Data Augmentation
If you have a very distorted video/image, would affine transformations of the images make object detection algorithms make more mistakes compared to a normal camera?
2
votes
0answers
26 views
Train a competitive layer on nonnormalized vectors using LVQ technique
How can we train a competitive layer on non-normalized vectors using LVQ technique ?
an example is given below from Neural Network Design (2nd Edition) book
The net input expression for LVQ networks ...
1
vote
2answers
71 views
How can we compute the gradient of max pooling with overlapping regions?
Studying CNN Back-propagation I can't understand how can we compute the gradient of max pooling with overlapping regions ?
That's also a question from this quiz and can be also found on this book .
3
votes
1answer
38 views
How to draw bounding boxes for gender classification?
I wonder what is the better way of drawing rectangles on images for gender classification. My task is to create a classifier (CNN based) to detect gender from pictures of entire bodies (not just faces)...
0
votes
1answer
68 views
How to compute number of weights of CNN?
How can we compute number of weights considering a convolutional neural network that is used to classify images into two classes :
INPUT: 100x100 gray-scale images.
LAYER 1: Convolutional layer with ...
