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
57 views

Relationship between input range and channel means, standard deviations for CNNs

So, I'm using a pretrained pnasnet5large model to do some image classification (https://github.com/Cadene/pretrained-models.pytorch/blob/master/pretrainedmodels/models/pnasnet.py) In the file, it ...
3
votes
2answers
1k views

Is pooling a kind of DropOut

If I got well the global idea of DropOut it allows to improve the sparsity of the information that come from one layer to another by setting some weights to zero. In another hand, pooling, let's say ...
1
vote
2answers
121 views

How to approach this handwritten digit recognition?

I have multiple pictures that look exactly like the one below this text. I'm trying to train CNN to read the digits for me. Problem is isolating the digits. They ...
1
vote
1answer
82 views

Recognition of small objects

I'm currently implementing an Android app for street sign recognition. My solution works quite well for the GTSRB dataset, since it provides a labeled test set of centered images. However, it doesn't ...
1
vote
2answers
502 views

How to get a binary output from a Siamese Neural Network

I'm trying to train a Siamese network to check if two images are similar. My implementation is based on this. I find the Euclidian distance of the feature vectors(the final flattened layer of my CNN) ...
1
vote
2answers
452 views

Keras giving memory allocation error and running extremely slow

I am working on character recognition using convolutional neural networks. I have 9 layer model and 19990 training data and 4470 test data. But when I am using keras with Tensorflow backend. When I ...
4
votes
2answers
138 views

How do randomly initialized neural networks behave?

I am wondering how the output of randomly initialized MLPs and ConvNets behave with respect to their inputs. Can anyone point to some analysis or explanation of this? I am curious about this because ...
2
votes
2answers
87 views

Can the same input for a plain neural network be used for a convolutional neural network?

Can the same input for a plain neural network be used for CNNs? Or does the input matrix need to be structured in a different way for CNNs compared to regular NNs?
2
votes
0answers
45 views

How a game playing agent could identify potential objects and proximity?

Most implementations I'm seeing for playing games like Atari (usually similar to DeepMind's work using DQN) have 4 graphical frames of input fed into 3 convolutional layers which are then fed into a ...
1
vote
1answer
73 views

Can I do oversampling by copying the same image multiple times? Will it effect my neural network accuracy?

I am working on an image data-set. As you may have guessed it is imbalanced data. I have 'Class A, 19,000 images' and 'Class B, 2,876 images'. So I did an undersampling by removing randomly from the ...
1
vote
0answers
33 views

How to preprocess a modified dataset so that a fitted CNN makes correct predictions on an un-modified version of the dataset?

for a school project I have been given a dataset containing images of plants and weeds. The goal is to detect when there is a weed in the pictures. The training and validation sets have already been ...
1
vote
1answer
215 views

Most efficient neural network for human activity recognition

A paper from machinelearningmastery.com on human activity recognition states that 1D convolutional neural networks work the best on classification of human activities using data from accelometer. But, ...
1
vote
1answer
81 views

Are commercially available neural ICs digital?

Apparently, one can buy a special-purpose integrated circuit (an IC like this one, for instance) to host a convolutional neural network. QUESTION Is such a circuit digital? Except for digital random-...
1
vote
1answer
32 views

Image prediction model when data-set classes have visual similarity

Lets say we have a data-set of all cats and we have to identify the cat breed based on given test image. As, the two different cat breeds have visual similarity can we use existing networks (VGG, ...
1
vote
0answers
63 views

Machine learning approach to facial recognition

First of all I'm very new to the field. Maybe my question is a bit too naive or even trivial... I'm currently trying to understand how can I go about recognizing different faces. Here is what I ...
2
votes
1answer
125 views

Why does the number of feature maps increases in the VGG model?

I found the below image of how a CNN works But I don't really understand it. I think I do understand CNNs, but I find this diagram very confusing. My simplified understanding: Features are ...
3
votes
3answers
99 views

Features Map convolutional neural network

I have a question about convolutional neural newtork. Consider this image: conv example We have a part of an input matrix and a filter. Ok, now we can do the convolution and the result is a scalar, ...
1
vote
1answer
242 views

What should a good loss curve look like?

This is a very basic question. I'm running a faster rcnn trainer on a dataset for object recognition. My images range from 200x200 to 7360x4912 in resolution. There are only 2 classes being trained (...
1
vote
1answer
30 views

Problem extracting features from convolutional layer where the dimensions are big for feature maps

I have trained a convolutional neural network on images to detect emotions. Now I need to use the same network to extract features from the images and use the features to train an LSTM. The problem is:...
10
votes
2answers
3k views

What is the difference between a receptive field and a feature map?

In a CNN, the receptive field is the portion of the image used to compute the filter's output. But one filter's output (which is also called a "feature map") is the next filter's input. What's the ...
1
vote
0answers
104 views

Multi-channel CNNs and channels

In language models, CNNs can extract different n-gram features from the input. From my current understanding, these models are called "multi-channel CNNs". I'm referring to these materials: https://...
2
votes
0answers
51 views

Using features extracted from a CNN as convolutional filter

I'm a bit confused about this. Assume I have a CNN network with two branches: Top Bottom The top branch outputs a feature vector of shape 1x1x1x10 (batch, h, w, c) The bottom branch outputs a ...
2
votes
1answer
2k views

How to combine input from different types of data sources?

I've to train a neural network using microphone data (wav files), accelerometer sensor data and light sensor data. Right now the approach I thought was to convert all data into images and combine ...
2
votes
1answer
67 views

How to measure the reasoning capabilities of neural networks

Which possibilities exist to evaluate the visual reasoning capabilities of neural networks in the field of image recognition? Are there methods to measure the ability of machine reasoning? Or ...
1
vote
0answers
74 views

neural network deconvolution filters

I understand the concept of convolution. Let's say that my input dimension is 3 x 10 x 10 And if I say that I will have 20 activation maps and a filter size of 5, ...
3
votes
1answer
190 views

Best way to create an image dataset for CNN

I am creating a dataset made of many images which are created by preprocessing a long time series. Each image is an array of (128,128) and the there are four classes. I would like to build a dataset ...
3
votes
3answers
754 views

Neural Network for Optical Mark Recognition?

I've created a neural net using the ConvNetSharp library which has 3 fully connected hidden layers. The first having 35 neurons and the other two having 25 neurons each, each layer with a ReLU layer ...
1
vote
0answers
24 views

If there are several computers on a subnet, can training time be reduced by distributing the work across them?

We have multiple computers and the ability to ssh between them. What are options using either Java, C/C++, JavaScript, or Python to distribute our learning tasks? We will be using DCNN, DQN, and LSTM ...
5
votes
1answer
238 views

Does it make sense to apply softmax on top of relu?

While working through some example from Github I've found this network (it's for FashionMNIST but it doesn't really matter). Pytorch forward method (my query in upper case comments with regards to ...
3
votes
0answers
44 views

What is meant by “model discriminability for local patches within the receptive field”?

In the Abstract section of the paper Network In Network, what does the authors actually mean to say?
5
votes
1answer
197 views

What are the ways to calculate the error rate of a deep Convolutional Neural Network, when the network produces different results using the same data?

I am new to the object recognition community. Here I am asking about the broadly accepted ways to calculate the error rate of a deep CNN when the network produces different results using the same data....
1
vote
1answer
796 views

Why are there transition layers in DenseNet?

The DenseNet architecture can be summarizde with this figure: Why there are transition layers between each block? In the papers, they justify the use of transition layers as follow : The ...
2
votes
1answer
195 views

Maxpooling in inception?

Maxpooling is performed as one of the steps in inception which yields same output dimension as that of the input. Can anyone explain how this max pooling is performed?
2
votes
1answer
41 views

Recognising Noise in Simple Classification

I have created a classifier for some simple gestures using an input layer, a hidden layer with tanh activation and an output softmax layer. I'm also using the Adam optimiser. The network classifies ...
4
votes
1answer
66 views

How to define a loss function for a classifier where the confusion between some classes is more important than the confusion between others?

I have a dataset of images belonging to $N$ classes, $A_1, A_2...A_n,B_1,B_2...B_m$ and I want to train a CNN to classify them. The classes can be considered as subclasses of two broader classes $A$ ...
0
votes
1answer
48 views

Inception neural network input layer confusion

According to the original paper on page 4, 224x224x3 image is reduced to 112x112x64 using a filter ...
1
vote
1answer
172 views

Is 1mb an acceptable memory size for images being trained in a CNN?

I am using Tensorflow CNN to build an image classification/prediction model. Currently all the images in the dataset are each about 1mb in size. Most examples out there use very small images. The ...
4
votes
2answers
4k views

How to handle rectangular images in convolutional neural networks?

Almost all the convolutional neural network architecture I have come across have a square input size of an image, like $32 \times 32$, $64 \times 64$ or $128 \times 128$. Ideally, we might not have a ...
1
vote
1answer
48 views

Huge variations in epoch count for highest generalized accuracy in CNN

I have written my own basic convolutional neural network in Java as a learning exercise. I am using it to analyze the MIT CBCL face database image set. They are a set of 19x19 pixel greyscale images. ...
5
votes
4answers
6k views

Traffic signs dataset

I'm looking for annotated dataset of traffic signs. I was able to find Belgium, German and many more traffic signs datasets. The only problem is these datasets contain only cropped images, like this: ...
2
votes
4answers
212 views

Using Convolutional Neural Networks for movement classification

I have programmed my first network for the MNIST dataset. I was wondering what the first approach would be to recognize certain movements. I have read about that the time dimension should be ...
0
votes
1answer
190 views

Using 3D Points as Inputs to a Neural Net

I am currently looking to use a neural network to classify gestures. I have a series of Dx,Dy,Dz readings that represent the differences across the three axes made during the gesture. About 10 ...
2
votes
0answers
36 views

Autoencoder why it is special for image decoding?

I have read about auto encoder. Understood what is encoding part, and decoding part, and the latent space. Now, i tried to implement this in keras. Below is the code. ...
3
votes
1answer
100 views

Can a basic CNN (Conv2D, MaxPooling2D, UpSampling2D) find a good approximation of a product of its input channels?

Let's assume I want to teach a CNN some physics. Starting with a U-Net, I input images A and B as separate channels. I know that ...
2
votes
1answer
60 views

Is there a way that helps me to architect my CNN fundamentally before training?

While we train a CNN model we often experiment with the number of filters, the number of convolutional layers, FC layers, filter size, sometimes stride, activation function, etc. More often than not ...
2
votes
0answers
11 views

How do we stack two U-Nets to yield one final prediction?

I am trying to reproduce the model described in the paper DocUNet: Document Image Unwarping via A Stacked U-Net, i.e. stacking two U-Nets to yield one final prediction. The paper mentions that: ...
1
vote
2answers
63 views

CNN Pooling layers unhelpful when location important?

I'm trying to use a CNN to analyse statistical images. These images are not 'natural' images (cats, dogs, etc) but images generated by visualising a dataset. The idea is that these datasets hopefully ...
1
vote
1answer
120 views

How can I classify relevant and irrelevant images from the Database?

I have a mixed image database(unstructured data). In the database there are some images that i am interested in and I want to discard the rest by using cnn. I am not looking for specific objects in ...
4
votes
1answer
344 views

Convolutional Layers on a hexagonal grid in Keras

Keras' convolutional and deconvolutional layers are designed for square grids. Is there was a way to adapt them for use in hexagonal grids? For example, if we were using axial coordinates, the input ...
3
votes
1answer
96 views

What is the dimensionality of the output map, given the dimensionality of the input map, number of filters, stride and padding?

I am trying to understand the dimensionality of the outputs of convolution operations. Suppose a convolutional layer with the following characteristics: Input map $\textbf{x} \in R^{H\times W\times D}...

1
10 11
12
13 14
16