Questions tagged [convolutional-neural-network]

A convolutional neural network is a form of neural network with an additional convolutional layer, typically used in image & audio analysis. The convolutional layer is essentially a filtering stage defined by the kernel which is used. For example, a convolutional layer could have a kernel which extracts edges from an image towards the goal of learning which objects are in a scene.

Filter by
Sorted by
Tagged with
6
votes
2answers
9k views

What is the input size of Alex net

In the paper ImageNet Classification with Deep Convolutional Neural Networks, the size of input image is 224x224. The following figure shows the input size. From caffe, deploy.prototxt file from the ...
6
votes
1answer
5k 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.
6
votes
3answers
332 views

Disparity between training and testing errors with deep learning: the bias-variance tradeoff and model selection

I am developing a convolutional neural network and have a dataset with 13,000 datapoints that is split 80%/10%/10% train/validation/test. In tuning the model architecture, I found the following, after ...
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 ...
6
votes
4answers
17k views

How to improve loss and avoid overfitting

I'm trying to build a 2 class image classifier using the architecture suggested in first part of this blog https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data....
6
votes
1answer
2k views

Convnet training error does not decrease

I'm training a convoluted neural net to drive a toy car, and no matter what I do the training accuracy does not increase beyond 30-35%, which is where it starts when the convnet is randomly ...
6
votes
3answers
5k views

How to combine GridSearchCV with Early Stopping?

I'm a beginner in machine learning and want to train a CNN (for image recognition) with optimized hyperparameter like dropout rate, learning rate and number of epochs. The optimal hyperparameter I ...
6
votes
1answer
6k views

It is helpful to normalize target variables for a regression neural network?

It is customary to normalize feature variables and this normally does increase the performance of a neural network in particular a CNN. I was wondering if normalizing the target could also help ...
6
votes
2answers
1k views

In a convolutional neural network (CNN), when convolving the image, is the operation used the dot product or the sum of element-wise multiplication?

The example below is taken from the lectures in deeplearning.ai shows that the result is the sum of the element-by-element product (or "element-wise multiplication". The red numbers ...
6
votes
3answers
6k views

Should there be a flat layer in between the conv layers and dense layer in YOLO?

Should there be a flat layer in between the conv layers and dense layer in YOLO? It's something not specified in the paper, but I see most implementations of YOLO on github do this. In my ...
6
votes
3answers
3k views

Binary classification of similar images with small region of interest

I have a dataset of microscope images and I want to train a ML/DL algorithm to perform binary classification. The positive class is when there is only one cell in the image, and the negative class is ...
6
votes
1answer
2k views

RELU vs Pooling

Does RELU means to change pixel value to 0 if it is negative anywhere , and later if we apply maximum pooling then what is the use of RELU because in this step we choose maximum value so no matter it ...
6
votes
1answer
3k views

Multi scale CNN Network Python

I created a multi-scale CNN in python keras. The network architecture is similar to the diagram. Here, same image is fed to 3 CNN's with different architectures. The weights are NOT shared. I ...
6
votes
2answers
2k views

Optimizing CNN network

I am currently trying to recreate the result of this paper, in which they do feature extraction from a "spectogram" of log-melfilter energies.. Since the paper doesn't state what kind of feature I ...
6
votes
3answers
4k views

Stuck on deconvolution in Theano and TensorFlow

I'm captivated by autoencoders and really like the idea of convolution. It seems though that both Theano and TensorFlow only support conv2d to go from an array of 2D-RGB (n 3D arrays) to an array of ...
6
votes
1answer
341 views

CNN or Viola-Jones for facial detection

I was wondering since CNNs have dominated every image-related task. Is the Viola-Jones face detector still considered state-of-the-art, or have CNNs surpassed its performance?
6
votes
1answer
221 views

Why is this not ordinary convolution?

I am currently studying this paper (page 53), in which the suggest convolution to be done in a special manner. This is the formula: \begin{equation} \tag{1}\label{1} q_{j,m} = \sigma \left(\sum_i \...
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 ...
5
votes
2answers
3k views

How to sort numbers using Convolutional Neural Network?

Recently, in an interview I got this question: Design a convnet that sorts numbers. Operators are ReLU, Conv, and Pooling. E.g. input: 5, 3, 6, 2; output: 2, 3, 5, 6 I am not sure how can you sort a ...
5
votes
3answers
2k views

Unbalanced training data for different classes

What precautions do I need to take while trying to develop a CNN for classification of images if there is much more training data for one label. For example: ...
5
votes
5answers
3k views

How to fix these vanishing gradients?

I am trying to train a deep network for twitter sentiment classification. It consists of an embedding layer (word2vec), an RNN (GRU) layer, followed by 2 conv layers, followed by 2 dense layers. Using ...
5
votes
4answers
200 views

What type of neural network should I use to detect meteors in images?

I am currently building a project that takes fisheye images from cameras and detects whether the picture contains a meteor, and if it does it tries to identify where the meteor is. The images look ...
5
votes
1answer
16k views

Keras Conv1D for simple data target prediction

I am trying to use conv1D layer from Keras for predicting Species in iris dataset (which has 4 numeric features and one categorical target). Following is my code: ...
5
votes
2answers
4k views

Correct number of biases in CNN

What is the correct number of biases in a simple convolutional layer? The question is well enough discussed, but I'm still not quite sure about that. Say, we have (3, 32, 32)-image and apply a (32, 5,...
5
votes
1answer
5k views

Convolutional neural network fast fourier transform

I've read that some convolution implementations use FFT to calculate the output feature/activation maps and I'm wondering how they're related. I'm familiar with applying CNNs, and (mildly) familiar ...
5
votes
1answer
3k views

What is the depth of an image in Convolutional Neural Network?

I am learning cs231n Convolutional Neural Networks for Visual Recognition. The lecture notes introduce the concepts of width, height, depth. For example, In CIFAR-10, images are only of size ...
5
votes
1answer
1k views

1x1 Convolution. How does the math work?

So I stumbled upon Andrew Ng's course on $1x1$ convolutions. There, he explains that you can use a $1x1x192$ convolution to shrink it. But when I do: ...
5
votes
1answer
796 views

Convolution Neural Network Loss and performance

I have a set of about ~100,000 training examples. Ratio of positive to negative example is roughly 1:2. The true ratio is more like 1:100 so this represents a major downsampling of the negative class. ...
5
votes
1answer
328 views

Data augmentation parameters

When I use data augmentation to increase the train dataset, should I use all augmentation techniques (parameters in keras)? Which data augmentation parameters should use with ...
5
votes
1answer
797 views

Feature selection by overfitting a small sample size

I am using a CNN based model to do sequence classification. Since training an entire dataset is very expensive, and I have a large set of features needed to try, its impossible for me to select ...
5
votes
1answer
310 views

Do Convolution Layers in a CNN Treat the Previous Layer Outputs as Channels?

Lets say you have a max pooling layer that gives 10 downsampled feature maps. Do you stack those feature maps, treat them as channels and convolve that 'single image' of depth 10 with a 3d kernel of ...
5
votes
1answer
298 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 ...
5
votes
1answer
111 views

Triplet loss function for face recognition?

In the Andrew-NG coursera course on Convnets he talked about triplet loss function for one shot face recognition. The formula given in the video is, $$\to \small \small \small ||f(A)-f(P)||^2 \;+\;\...
5
votes
1answer
231 views

What is the point of tensors in CNNs? Why not simply reshape the data into matrices?

Take the following tensor: $$ \left[\begin{array}{cc} a & b & c\\ d & e & f\\ g & h & i\\ \end{array}\right] $$ $$ \left[\begin{array}{cc} j & k & l\\ o & n & ...
5
votes
2answers
1k views

Tensorflow oscillating Test and Train Accuracy?

I have implemented a CNN with images as input and 101 classes as output. I have applied mean subtraction and normalization to the input before giving it as input to the network. I have also ...
5
votes
1answer
3k views

Are CNNs best approaches to find and count objects in images?

I'm starting my first real data-science project, I made a reserach and want to ask if my approach is correct: I HAVE: 600 photos of electronic components, hundreds of components in a single ...
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
2answers
459 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 ...
5
votes
2answers
2k views

Overfitting in Siamese Network

I am trying to train a Siamese network for an application very similar to this and this. From what I have read about training Siamese networks dissimilar pairs of images outnumber the similar pairs ...
5
votes
1answer
195 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 ...
5
votes
3answers
378 views

How can I know if my conv1D model is overfitted or underfitted from loss curve?

I am working on classification of time series multivariate data. By doing PCA, I converted multivariate to uni-variate and fed it into a conv1d in keras. However, I am getting a very high accuracy ...
5
votes
0answers
66 views

Training value neural network AlphaGo style

I have been trying to replicate the results obtained by AlphaGo following their supervise learning protocol. The papers specify that they use a network that has two heads: a value head that predicts ...
5
votes
1answer
2k views

Gradient flow through concatenation operation

I need help in understanding the gradient flow through a concatenation operation. I'm implementing a network (mostly a CNN) which has a concatenation operation (in pytorch). The network is defined ...
4
votes
4answers
7k views

Is There any RNN method used for Object detection

after reading the state of the art about object detection using CNN (R-CNN Faster R-CNN ,YOLO, SSD...) I was wondering if there is a method that use RNN's or that combine the use of CNN's and RNN's ...
4
votes
3answers
4k views

Deep neural networks for mostly zero valued data

I have some data with around 1000 features. Problem is most of the features are 0. In each row usually around 100 features have values and rest of the features are 0. A sample example data is given ...
4
votes
1answer
1k views

What is deconvolution operation used in Fully Convolutional Neural Networks?

When I was reading this this paper, Fully Convolutional Networks for Semantic Segmentation, I found that they use an up-sampling layer to classify each pixel in to a class. I have two questions: How ...
4
votes
1answer
150 views

Estimating Titan X graphics card impact on performance

I'm currently training CNNs using Tensorflow (Python) on my GTX 970 (specs here). I recently took a look at the new pascal based Titan Xs and I'm wondering what an estimated performance/speed gain ...
4
votes
2answers
7k 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 ...
4
votes
2answers
2k views

Is Maxout the same as max pooling?

I've recently read about maxout in slides of a lecture and in the paper. Is maxout the same as max pooling?
4
votes
2answers
4k views

A deep learning approach that can calculate distance to obstacles

After reading about the most famous object detection CNN based methods: YOLO, YOLO 9000, r-cnn, faster r-cnn, etc., I was wondering if there is an architecture that can calculate the distance to the ...

1
2
3 4 5
12