Questions tagged [convolutional-neural-networks]
For questions about convolutional neural networks, also known as CNN or ConvNet.
0
votes
0answers
7 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 ...
-2
votes
0answers
17 views
Practical usage of face embedding for face recognition tasks
I have a Facenet-like model that has been trained on faces of different identities and allows to build embedding of input faces. The training set includes N identities, $[I_1, I_2 ... I_N]$.
I want ...
-1
votes
0answers
12 views
Data augmentation with ImageDataGenerator in Keras - Python
I have tried to use imageDataGenerator for data augmentation for following cnn wich i need to train for 5 different image classes. When i run this code, following error occurred.
"Traceback (most ...
1
vote
1answer
12 views
Neural Network for OMR?
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 ...
2
votes
0answers
16 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
44 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 ...
1
vote
0answers
9 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?
4
votes
1answer
27 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....
0
votes
1answer
18 views
Why is there Transition layers in DenseNet?
The DenseNet architecture can be summarize with this figure :
Why there is transition layers between each blocks ?
In the papers, they justify the use of transition layers as follow :
The ...
2
votes
1answer
19 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?
1
vote
1answer
17 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
39 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
24 views
Inception neural network input layer confusion
According to the original paper on page 4, 224x224x3 image is reduced to 112x112x64 using a filter ...
0
votes
1answer
28 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 ...
1
vote
2answers
56 views
how to handle rectangle images in neural network?
Almost all the neural network architecture I have come across have a square input size of an image. like 32x32,64x64,128x128,.......
Ideally we might not have a ...
0
votes
0answers
9 views
Adapting the U-net architecture for non-square images
I have been working on developing an image downsampling algorithm based on a certain phsycophysical technique. I have constructed a dataset having 40 images, where the input images have size 256x350 ...
1
vote
1answer
25 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.
...
4
votes
3answers
82 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
59 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 ...
-1
votes
1answer
30 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
28 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
23 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 ...
1
vote
1answer
29 views
Fundamentally choosing number & size of filters, convolution layers in deep learning
While we train a CNN model we often experiment with number of filters, number of convolutional layers, FC layers, filter size, sometimes stride, activation function, etc. More often than not after ...
1
vote
0answers
7 views
How do we stack two U-Nets to yield one final prediction?
I am trying to reproduce this paper's model, i.e. stacking two U-Nets to yield one final prediction. The paper mentions that:
The deconvolution features of the first U-Net and the intermediate
...
0
votes
2answers
29 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 ...
0
votes
1answer
76 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 ...
0
votes
0answers
54 views
How can I deal with 4 channel image with pytorch?
I have 4 channel RGB-D data.
(RGB 3-channel image with depth information per pixel)
What I want is, use these data as input for trained network (and this one is not made by me.).
However, this ...
1
vote
0answers
20 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 ...
1
vote
1answer
32 views
Dimensionality of convolutional layers & convolution operations
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}...
0
votes
0answers
26 views
Correct implementation of backpropagation / gradient calculation for a single kernel convolutional neural network
I have coded a convolutional neuronal network with just one filter/kernel which slides over a word embedding with a dimension of 100. With a kernel size of 4x1, I got a feature map $m$ with the size ...
1
vote
0answers
35 views
Doubt regarding research paper on Crowd Counting using Convolutional neural networks and Markov Random Field
I am currently reading the research paper Image Crowd Counting Using Convolutional Neural Network and Markov Random Field by Kang Han, Wanggen Wan, Haiyan Yao, and Li Hou.
I did not understand the ...
3
votes
2answers
66 views
Can I reduce the “number of weights” in CNN to 1/3 by restricting the input as greyscale image?
In a CNN, does each new filter have different weights for each input channel, or are the same weights of each filter used across input channels?
This question helps me a lot.
Let, I have RGB input ...
2
votes
1answer
45 views
Clarification regarding “Image Crowd Counting Using Convolutional Neural Network and Markov Random Field”
I am currently reading the research paper Image Crowd Counting Using Convolutional Neural Network and Markov Random Field by Kang Han, Wanggen Wan, Haiyan Yao, and Li Hou.
I did not understand the ...
1
vote
1answer
60 views
Occupation detection using Face API
For my university project, I am planning to build a face recognition/ occupation recognition programme. However, rather than using the existing Haar cascade(for age and gender) I am planning to use ...
2
votes
1answer
34 views
How to architect a network to find bounding boxes in simple images
I have an application where I want to find the locations of objects on a simple, relatively constant background (fixed camera angle, etc). For investigative purposes I've created a test dataset which ...
6
votes
2answers
148 views
Which layer consumes more time in CNN training ? Convolution layers vs FC layers
In Convolutional Neural Network, which layer consumes maximum time in training? Convolution layers or Fully Connected layers? We can take AlexNet architecture to understand this. I want to see time ...
0
votes
0answers
10 views
Is there an optimal number of deconvolution layers?
Transposed convolution layers (aka deconvolution layers) are typically used to upsample an image after several pooling steps and bring it back to the original size (e.g. semantic segmentation, encoder-...
1
vote
1answer
50 views
Counting people in an image of a crowd
What are some good approaches that I can use to count the no. of people in a crowd. Tracking each person individually is obviously not an option. Any good approaches or some references to research ...
2
votes
2answers
38 views
What benefits can be got by applying Graph Convolutional Neural Network instead of ordinary CNN?
What benefits can we got by applying Graph Convolutional Neural Network instead of ordinary CNN? I mean if we can solve a problem by CNN, what is the reason should we convert to Graph Convolutional ...
-1
votes
1answer
40 views
Simple Object Detection
I want to create a simple Object detection tool. So basically an Image will be provided to the tool and from that, it has to detect the number of objects.
For eg
An image of a dining table which ...
4
votes
1answer
31 views
Optimizing image recognition results for unknown labels
I’m training a network to do image classification on zoo animals.
I’m a software engineer and not an ML expert, so I’ve been retraining Google’s Inception model and the latest models is trained ...
0
votes
0answers
38 views
Loss is saturated and not chaging even after learning rate decay
I'm using a Convolutional Denoising Autoencoder neural network for Audio Source Separation. I'm using SGD Momentum. My initial <...
3
votes
1answer
29 views
Figuring out mapping between two matrices
Imagine I have a 2D matrix, A. I apply some transformation to it, for example:
B = A_shifted + A.
Would it be possible to train a CNN to learn back the mapping from B to A? Giving B as example and A ...
3
votes
1answer
81 views
How to tinker with CNN architectures?
I was thinking of creating a CNN. Now it is known CNN takes long times to train so it is advisable to stick to known architectures and hyper-parameters.
My question is: I want to tinker with the CNN ...
1
vote
0answers
24 views
YOLO - How much is the position of the object relevant in learning?
I have the following question about You Only Look Once (YOLO) algorithm, for object recognition in CNNs.
I have to develop a neural network to recognize web components in web applications - for ...
4
votes
1answer
34 views
How to compare the training performance of a model on different data input?
So I have a deep learning model and three data sets (images). My theory is that one of these data sets should function better when it comes to training a deep learning model (meaning that the model ...
0
votes
0answers
24 views
What is the architecture of net, that takes an image as input and gives a number(no classes) as output?
I am new, so i only know that the first layers must be a conv net, but how can i get a number instead of classes? For example: get an angle of something using a photo.
4
votes
1answer
169 views
Training a CNN from scratch over COCO dataset
I am using Tensorflow Object Detection API for training a CNN from scratch on COCO dataset. I need to use this specific configuration.
There is no pre-trained model on COCO with that configuration and ...
4
votes
1answer
60 views
How to train a CNN
When it comes to CNNs, I don't understand 2 things in the training process:
How do I pass the error back when there are pooling layers between the convolutional layers?
And if I know how it's done, ...
4
votes
0answers
28 views
How should continuous action/gesture recognition be performed differently than isolated action recognition
I am going to train a deep learning model to classify hand gestures in video. Since the person will be taking up nearly the entire width/height of the video and I will be classifying what hand gesture ...
