Questions tagged [convolutional-neural-networks]

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

Filter by
Sorted by
Tagged with
10
votes
3answers
1k views

Using neural network to recognise patterns in matrices

I am trying to develop a neural network which can identify design features in CAD models (i.e. slots, bosses, holes, pockets, steps). The input data I intend to use for the network is a n x n matrix (...
1
vote
1answer
515 views

How are kernel's input values initialized in a CNN network?

I am currently learning about CNN's and I am confused on how filter/kernels are initialized beside their size? Say if you want a filter of 3x3 how are the inner values initialized a the start? http:/...
6
votes
3answers
3k views

Using machine learning to identify CAD model features

I am trying to develop a machine learning algorithm to identify topological features within 3D CAD models (i.e. slots, pockets, holes, bosses etc) For the input data I have decided to use the ...
1
vote
2answers
175 views

Why does ReLU (and other non linearities) work?

Can someone please point me to where I can read up on why non linearities that can produce values larger than 1 or smaller than 0 work. My understanding is that neurons can only produce values between ...
3
votes
1answer
67 views

Predict value from image set

I have a large dataset of skin images, each one associated with a hydration value (percentage). Now I'm looking into predicting the hydration value from an image. My thinking: train a CNN on the ...
4
votes
1answer
78 views

Is one big network faster than several small ones?

The basis of my question is that a CNN that does great on MNIST is far smaller than a CNN that does great on ImageNet. Clearly, as the number of potential target classes increases, along with image ...
1
vote
0answers
43 views

Regarding Tensorflow: How to Avoid Duplicate Use of Scope/Variable_names

I am trying to train Chess data through CNN. To proceed reinforcement learning, I had divided into two - "current network" and "reinforcement network". For each checkpoint file stored in different ...
9
votes
2answers
1k views

Use AI or Neural Network for logo detection

I am trying to detect a TV channel logo inside a video file, so simply given an input .mp4 video, detect if it has that logo present in a specific frame, say first ...
3
votes
1answer
760 views

Trying to understand VGG convolution neural networks architecture

Trying to understand the VGG architecture and I have these following questions. I understand the general understanding of increasing filter size is because we are using max pooling and so its image ...
4
votes
1answer
384 views

CNN for pattern recognition without a training set

I have a 10gb file of a time series 1D signal. I want to find some patterns within this signal, I know CNN's are great for this but the problem is I don't have any training data. Now I could of ...
9
votes
5answers
5k views

What is the fundamental difference between CNN and RNN?

What is the fundamental difference between convolutional neural networks and recurrent neural networks? Where are they applied?
1
vote
0answers
319 views

Similarity of images (CBIR) with CNN features

I am trying to build a neural network suitable to measure similarity between pairs of images. In particular I am interested in shoes. I have a query image (e.g. a shoe that I just took a picture of) ...
1
vote
1answer
2k views

What fast loss convergence indicates on a CNN?

I'm training two CNNs (AlexNet e GoogLeNet) in two differents DL libraries (Caffe e Tensorflow). The networks was implemented by dev teams of each libraries (here and here) I reduced the original ...
1
vote
1answer
343 views

What is the meaing of 2D stride

I know what meaning stride has when it is just an integer number (by which step you should apply filter to image). But about (1, 1) or even more dimensional stride?
1
vote
1answer
100 views

Can CNN autoencoders be improved by treating the output layer as an inverted hidden layer?

I wish to write a bot that can use screen footage to play a game, specifically for the game 'Nidhogg'. To that end I have determined that a CNN should do the feature detection and a feedforward ...
3
votes
3answers
282 views

Would convolutional NN recognize patterns in encoded images?

I have a set of images that I already trained a CNN to classify successfully. I wonder if it would be possible to encode the images (using XOR in combination with a key of the same length as the image)...
4
votes
2answers
2k views

Can Convolutional Neural Networks be applied in domains other than image recognition?

I'm new in this argument, my question is: Can convolution be applied in other contexts different from image recognition? Is there a good source to learn from?
14
votes
2answers
1k views

What's the main concept behind Capsule Networks? [duplicate]

As you might know, Capsule Networks have been recently introduced by Hinton. There also have been several heads up within his talks. As expected, the paper elaborates on the idea way theoretically! ...
2
votes
1answer
355 views

Constraining the output value range of a CNN independent of the loss function

I'm having the following problem: ` I'm training a multi-output CNN and using the relative values of the outputs in my loss function. The net is learning well, but as the absolute values of the ...
6
votes
4answers
1k views

Why my test error is lower then train error

I am trying to train a CNN regression model using the ADAM optimizer, dropout and weight decay. My test accuracy is better than training accuracy. But as I know, usually train accuracy is better than ...
2
votes
1answer
686 views

What are the counterparts of non-linearities and dropout in fully convolutional networks?

I am trying to replicate the fully convolutional networks (FCN) concept described here for semantic segmentation. It seems people have successfully trained such models by removing fully connected ...
4
votes
1answer
2k views

How to train for own dataset really really fast while debugging

How to train darkflow for my custom object really really fast during debugging in quad core PC and without GPU? (Can I train with about 10 images and test with only those images, just to check if all ...
3
votes
3answers
95 views

Method for Multi-class/category?

I am having issues getting started with a multi class problem with multiple features and hoping someone could please point me in the right direction. I have data that is structured like this for ...
1
vote
0answers
47 views

Can Image Recognition used to find height of a person whole, torso, legs etc

Image recognition can be used to classify images. But I wanted to find few parameters like height of person, his legs, his hand etc. Will CNN helpful for this type of output ?
2
votes
0answers
46 views

Recommendations on which architecture to use to guess appointment

I'm currently developping an application which allows psychologists to manage their schedule and budget. As a proof of concept, I would like to create an intelligent appointment service. There can be ...
5
votes
1answer
480 views

What makes learned feature detectors specialize in CNN?

It has been shown that it is possible to use unsupervised learning techniques to produce good feature detectors in CNNs. I can't understand what drives specialization of those feature detectors. In ...
2
votes
0answers
181 views

Can anybody explain such behavior of accuracy and loss of my Net(caffe)?

I used this project for example(framework - caffe, arhitecture of net - mod of AlexNet, 400 images are used for training). I have this result: or this: Solver: ...
3
votes
1answer
1k views

How to detect the empty parking spots?

I have some images of the empty parking as shown below. I 'd like to use deep learning to extract the parking spots. But in the beginning,am confused whether there are several ways to do the ...
3
votes
1answer
177 views

ReLu, Sum and Convolution Layers to Count Pixels of Certain Color

Below is an excerpt in an instructor's manual on ML that is explaining deep neural networks, using cat recognition (what else!) from images as example. On how DL performs this feat, the excerpt said ...
4
votes
0answers
141 views

Game AI - Modify image classification model for analog output

I'm developing a Game AI which tries to master racing simulation. I already trained a CNN (alexnet) on ingame footage of me playing the game and the pressed keys as the target. I had two main issues ...
5
votes
1answer
394 views

Game AI - Fast python OCR or cropped image input

I'm developing a Game AI which tries to master racing simulations. I already trained a CNN (alexnet) on ingame footage of me playing the game and the pressed keys as the target. As the CNN is only ...
0
votes
1answer
4k views

Book recommendations on deep learning (convolutional neural networks) [closed]

I am working on software which deblurs the motion blur created by camera movement. I've surveyed some research papers and determined this process requires deep learning and CNN. Now I'm looking for ...
4
votes
1answer
711 views

Training Custom object detection network using tensor-flow object detection API?

I was just wondering if some one could provide a nice tutorial on how to use the Recent tensor-flow object detection API to train custom network say like VGG-16? (Just USE the VGG-16, VGG-19, ...
3
votes
2answers
164 views

Will CNNs kill CAPTCHAs or can they survive in an evolved form?

CAPTCHAs, which are often seen in web applications, are working under the assumption, that they pose a challenge which a human can solve easily while a machine will most likely fail. Prominent ...
3
votes
1answer
489 views

Intuitively understanding translational invariance in CNNs

I'm currently in the process of learning about using CNNs in image recognition. Many of the different resources I read that were explaining the motivation referred to the fact that these networks are (...
14
votes
3answers
21k views

How to handle images of large sizes in CNN?

Suppose there are 10K images of sizes 2400 x 2400 are required to use in CNN.Acc to my view conventional computers the people use will be of use. Now the question is how to handle such large image ...
5
votes
2answers
89 views

What defines a good dataset in Deep Learning approach?

Scenario: I am trying to create a dataset with images of choice for different animal classes. I am going to train those images for classification using CNN. Problem: Lets assume I somehow don't have ...
5
votes
2answers
92 views

CNNs: What happens from one neuron volume to the next?

I've gone through several descriptions of CNNs online and they all leave out a crucial part as if it were trivial. A "volume" of neurons consists of several parallel layers ("feature maps"), each the ...
2
votes
0answers
304 views

CNN attention maps on non-images

My datasets are not actual images, so using methods with ImageDataGenerator or pre-trained networks might not apply in this case. Data Structure: Each "image" is a 2048-long vector that has float ...
1
vote
3answers
742 views

Ensemble Learning using Convolutional Neural Networks

I have created 22 different Convolutional neural networks that all test for the presence of unique objects in an image (each one of the classifiers is unique). Each sample in the test set has the ...
0
votes
2answers
242 views

Feature extraction other than convolutions for images?

Are there approaches other than convolutions to learn features from images? Has there been any research to use approaches such as hashing (e.g. p-hash, ...
3
votes
0answers
149 views

How to feed a variable size sequences into a CNN?

If I want to train a convoluted NN on time series but I cannot decide where to split the data. I see that other people use jumping window over the input. so the feed say 20 sec of observation as 1 ...
2
votes
1answer
813 views

How can I use a trained CNN to predict a new image label?

I was applying this CNN fine-tuning example from Matlab. The example shows how to fine-tune a pre-trained CNN on letters to classify images of digits. Now I would like to use this new fine-tuned CNN ...
7
votes
3answers
5k views

How do we choose the kernel size depending on the problem?

Obviously, finding suitable hyper-parameters for a neural network is a complex task and very problem or domain-specific. However, there should be at least some "rules" that hold most times for filter ...
3
votes
3answers
8k views

How to “combine” two images for CNN input (classification task)?

For a classification task (I'm showing a pair of exactly two images to a CNN that should answer with 0 -> fake pair or 1 -> real pair) I am struggling to figure out how to design the input. At the ...
3
votes
2answers
3k views

How is the depth of a CNN layer determined?

I am looking at a diagram of ZFNet in an attempt to understand how CNNs are designed effectively. I'm working with the CIFAR10 set in pytorch. In the first layer, I understand the depth of 3 (...
1
vote
2answers
2k views

Create your own CNN in java or c#? [closed]

I would love to learn how to create my own neural network from scratch so i can understand them better. My goal it's not so much to use their perception capabilities (classifying pictures) as it is to ...
0
votes
1answer
102 views

How to deal with changing video frame sizes in a CNN?

How to deal with videos where the frame sizes are not the same frame to frame? For example this video moves up and down and when it does, the video part of the screen has a different amount of pixels ...
2
votes
1answer
155 views

Training a convolutional network to recognize object location

I am beginning an image analysis project to recognize images with a particular object centered on the image. If the object is at the center, I give the image a positive label, and if it is anywhere ...
3
votes
2answers
810 views

Is there any proof based literature out there on neural networks?

Is there any mathematical proof (like in proof of a theorem) based literature out there on neural networks ? Everything is empirically based but no math proof for instance on why certain parameters ...