Questions tagged [convnet]

For questions regarding "Convolutional Neural Networks" (CNN)

Filter by
Sorted by
Tagged with
27
votes
6answers
10k views

Why do convolutional neural networks work?

I have often heard people saying that why convolutional neural networks are still poorly understood. Is it known why convolutional neural networks always end up learning increasingly sophisticated ...
6
votes
1answer
2k views

Adjusting weights in an convolutional neural network

I'm trying to implement a convolutional neural network at the moment. A simple feedforward network is not the problem but I'm having some trouble with the weight adjustment in the conv layer. Lets ...
1
vote
1answer
2k views

shape of theano tensor variable out of keras Conv2D

Being new to theano, pls bear with me. I thought the shape of the tensor variable is already well defined out of the Conv2D layer since the input is specified, as follow, ...
1
vote
2answers
99 views

How to build a network that detects common object in images?

I have a group of images. All contain some common object (let's assume all at the same size and no other alterations). I want to train a CNN that will learn the filter for the common object and gives ...
4
votes
1answer
241 views

How are per-layer-detected-patterns in a trained CNN plotted?

In the case my question is not clear, I am talking about the patterns that are detected in each of the layers of an image-trained Convolutional Neural Network (CNN). Take the following image as an ...
7
votes
3answers
3k views

Convolutional Neural Network overfitting

I built a CNN to learn to classify EEG data (only about 4000 training examples, 2 classes, 50-50 class balance). Each training example is 64x512, with 5 channels each Ive tried to keep the network as ...
6
votes
1answer
4k views

Sigmoid vs Relu function in Convnets

The question is simple: is there any advantage in using sigmoid function in a convolutional neural network? Because every website that talks about CNN uses Relu function.
0
votes
2answers
280 views

My first machine learning experiment , model not converging , tips? [closed]

I wanted to recreate the model mentioned in this paper:https://arxiv.org/pdf/1610.09204v1.pdf . I am using keras with tensorflow backend, and a gtx 1050ti. I am an ML beginner, and thought this would ...
3
votes
1answer
839 views

Steps for back propagation of convolutional layer in CNN

Imagine I have the following layers in a CNN: Conv-layer 1 (without reLU) [3 filters @ 1x3x3] => ReLU-layer 1 => Maxpooling-layer 1 [2x2] Conv-layer 2 (without reLU) [10 filters @ 3x4x4] => ReLU-...
19
votes
4answers
27k views

What is the difference between Inception v2 and Inception v3?

The paper Going deeper with convolutions describes GoogleNet which contains the original inception modules: The change to inception v2 was that they replaced the 5x5 convolutions by two successive ...
6
votes
1answer
3k views

Convolutional autoencoders not learning

I'm trying to implement convolutional autoencoders in tensorflow, on the mnist dataset. The problem is that the autoencoder does not seem to learn properly: it will always learn to reproduce the 0 ...
3
votes
1answer
125 views

How do CNNs use a model and find the object(s) desired?

Background: I'm studying CNN's outside of my undergraduate CS course on ML. I have a few questions related to CNNs. 1) When training a CNN, we desire tightly bounded/cropped images of the desired ...
3
votes
1answer
892 views

How is the evaluation setup for YouTube faces of FaceNet?

The YouTube Faces database (YTF) consists of 3,425 videos of 1,595 different people. Given two videos, the task for YTF is to decide if they contain the same person or not. Having $n$ comparisons, the ...
1
vote
1answer
598 views

What are interleaved layers of convolutions?

In the FaceNet paper, they describe the Zeiler&Fergus model like this: [...] the Zeiler&Fergus model which consists of multiple interleaved layers of convolutions, [...] What do they ...
1
vote
0answers
741 views

Image as input and output in keras

I am trying to make a model of this image. Here is the relevant code: ...
3
votes
0answers
630 views

Are non-zero paddings used?

I currently tried to figure out which paddings are directly supported by the frameworks: Tensorflow (tf.nn.conv2d): ...
8
votes
3answers
2k views

Convolutional Neural Network not learning EEG data

I have trained a simple CNN (using Python + Lasagne) for a 2-class EEG classification problem, however, the network doesn't seem to learn. loss does not drop over epochs and classification accuracy ...
3
votes
2answers
548 views

Did anybody ever use mean pooling and publish it?

I found a couple of sources which mention mean pooling for convolutional neural networks (CNNs) - including all lectures I had about CNNs so far - but I could not find any paper with at least 10 ...
4
votes
1answer
264 views

Why do CNNs with ReLU learn that well?

Convolutional Neural Networks (CNNs) use almost always the rectified linear activation function (ReLU): $$f(x) = max(0, x)$$ However, the derivative of this function is $$f'(x) = \begin{cases} 0 &...
1
vote
1answer
739 views

Convolutional Neural Network: learning capacity and image coverage

I was looking through a CNN tutorial and towards the end they refer to learning capacity and image coverage during network learning diagnostics What do those 2 terms mean in the context of a ...
1
vote
0answers
409 views

Fully Convolutional Network: How To

I have studied the paper Fully Convolutional Networks for Semantic Segmentation (Shelhamer, Long and Darrell) and understand the process. They provide extensive code in Caffe. I have been analyzing ...
1
vote
0answers
77 views

Neural Network: how to utilize weakly-/unsupervised data to improve supervised network?

Let's consider one has built a fully-supervised neural network for some task, e.g. localizing an object in various scenes. As you can imagine, it is quite time-consuming to label data: one has to ...
1
vote
0answers
147 views

Do I have to use neural networks in a generative adversarial network?

I've only seen examples that use (various types of) neural networks for both the discriminative and generative model. Is it not sound to use say, a logistic regression model for the discriminative ...
2
votes
1answer
2k views

applying convolutional neural network over text documents using 1-D tf-idf feature vectors

I want to apply a CNN over documents. I have tf-idf vectors of documents with me (one vector per document). My question is, is 1D CNN applicable in this case? The reason I am asking this question is ...
2
votes
2answers
98 views

Is there any public implementation / publication with Hintons capsules idea?

In Hintons talk "What's wrong about convolutional nets" (Late 2016 or early 2015, I guess) he talks about capsules to make a modular CNN. Is there any publicly available implementation or papers ...
3
votes
2answers
4k views

Overfitting after first epoch

I am using convolutional neural networks (via Keras) as my model for facial expression recognition (55 subjects). My data set is quite hard and around 450k with 7 classes. I have balanced my training ...
1
vote
2answers
172 views

How can I create a classifier using the feature map of a CNN?

I intend to make a classifier using the feature map obtained from a CNN. Can someone suggest how I can do this? Would it work if I first train the CNN using +ve and -ve samples (and hence obtain the ...
2
votes
2answers
2k views

Training Validation Testing set split for facial expression dataset

I am using Convolutional Neural Networks (CNN) and I just want to ask if the way I split my training/validation/testing set is correct. I have a total of 55 subjects. I plan to split them into 80–10–...
1
vote
1answer
97 views

Unable to figure out nInputPlane in SpatialConvolution in torch?

Documentaion for Spatial Convolution define it as module = nn.SpatialConvolution(nInputPlane, nOutputPlane, kW, kH, [dW], [dH], [padW], [padH]) nInputPlane: The ...
1
vote
1answer
265 views

CNN tagging such that each input could have multiple tags

Thanks in advance for reading my question! I've been using CNNs to classify text using Keras and TF. My data is strings "I read the news" or "I read machine learning news" and my labels are tags: ...
1
vote
0answers
337 views

Do all layers have the same computational complexity in a ResNet?

Reading the ResNet paper, paragraph 3.3: The convolutional layers mostly have 3×3 filters and follow two simple design rules: (i) for the same output feature map size, the layers have the same ...
8
votes
1answer
507 views

Why does “Depth = Semantic representation” in convolutional neural networks?

I was watching some videos online about convolutional networks, and the speaker was discussing the concept of running a filter over an image. He said, and it is also shown in the image below, that "...
5
votes
1answer
3k views

Max-pooling vs. zero padding: Loosing spatial information

When it comes to convolutional neural networks there are normally many papers recommending different strategies. I have heard people say that it is an absolute must to add padding to the images before ...
5
votes
1answer
173 views

Highly accurate convnets appear to have random-looking visualized weights?

I'm building a TensorFlow convoluted neural network that isn't getting the accuracy that I hoped for. So I figured I would visualize the learned weights to see where the network might be stumbling. As ...
14
votes
1answer
4k views

Back-propagation through max pooling layers

I have a small sub-question to this question. I understand that when back-propagating through a max pooling layer the gradient is routed back in a way that the neuron in the previous layer which was ...
14
votes
2answers
18k views

How many images per class are sufficient for training a CNN

I'm starting a project where the task is to identify sneaker types from images. I'm currently reading into TensorFlow and Torch implementations. My question is: how many images per class are required ...
4
votes
0answers
261 views

how to propagate error from convolutional layer to previous layer?

I've been trying to implement a simple convolutional neural network. But I've been stuck at this problem for over a week. To be specific, assume there are 3 layers in a convolutional pass, marked as ...
69
votes
4answers
29k views

How are 1x1 convolutions the same as a fully connected layer?

I've recently read Yan LeCuns comment on 1x1 convolutions: In Convolutional Nets, there is no such thing as "fully-connected layers". There are only convolution layers with 1x1 convolution kernels ...
0
votes
1answer
114 views

How to architect ConvNet to ignore top half of image

I'm building a convoluted neural network to teach a toy car, powered by a Raspberry Pi, how to drive based on incoming streams of frames from a webcam mounted on top of the car. The top half of each ...
6
votes
2answers
1k views

Is there a known convolutional net architecture to calculate object masks for images?

I would like to train a convnet to do the following: Input is a set of single channel (from black to tones of grey to white) pictures with a given object, let's say cars. Target is, for every picture ...
1
vote
0answers
1k views

What are the advantages/disadvantages of using Autoencoders over CNNs for image search?

I've seen both of these techniques be used for image search. One difference I can think of is that autoencoders don't rely on labeled data. I'm not sure, but it seems logical therefore that they can ...
1
vote
1answer
662 views

LeNet for Convolution network?

I keep seeing LeNet used to referring to a convolution network? I am wondering why LeNet is called LeNet? Is it the abbreviation of anything? Is there a difference between LeNet and convolutional ...
8
votes
5answers
9k views

Convolutional Neural Networks in R

I don't see a package for doing Convolutional Neural Networks in R. Has anyone implemented this kind of algorithm in R?
0
votes
2answers
2k views

cifar10 official keras example not giving expected accuracy, using sigmoid seems better than relu

In the official Keras example cifar10 there is the following code to train a CNN using keras10. When I tried it, my neural net would not learn at all, I always get around a 10% acuracy, which is ...
11
votes
3answers
27k views

Question about bias in Convolutional Networks

I am trying to figure out how many weights and biases are needed for CNN. Say I have a (3, 32, 32)-image and want to apply a (32, 5, 5)-filter. For each feature map I have 5x5 weights, so I should ...
2
votes
1answer
192 views

Trying to figure out how to set weights for convolutional networks

I am working on CNN, and I have some doubts. Let's assume I only want one feature map, just to make things easier. And let's suppose my image is grayscale, to make things even easier. So, let's say my ...
7
votes
1answer
15k views

border_mode for convolutional layers in keras

Keras has two border_mode for convolution2D, same and valid. Could anyone explain what "same" does or point out some documentation? I could not find any document on the net (except people asking that ...
2
votes
1answer
129 views

Applying ConvNets to classify motion/video data

How would someone go about using deep learning to classify sign language gestures? For example, suppose I had video files of many different gestures. For any given gesture, I might have many videos of ...
5
votes
2answers
325 views

How to predict on part of image after training on other part of image?

I have images of identity cards (manually taken so not of same size) and I need to extract the text in it. I used tesseract to predict bounding boxes for each letter and am successful to some extent ...
11
votes
2answers
7k views

Document classification using convolutional neural network

I'm trying to use CNN (convolutional neural network) to classify documents. CNN for short text/sentences has been studied in many papers. However, it seems that no papers have used CNN for long text ...

1
6 7 8
9
10