Questions tagged [convolutional-neural-networks]

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

Filter by
Sorted by
Tagged with
2
votes
0answers
32 views

Does a fully convolutional network share the same translation invariance properties we get from networks that use max-pooling?

Does a fully convolutional network share the same translation invariance properties we get from networks that use max-pooling? If not, why do they perform as well as networks which use max-pooling?
1
vote
0answers
11 views

Why is the loss of one of the outputs of a model with multiple outputs increasing while the others are decreasing?

I'm a newbie in neural networks. I'm trying to fit my neural network that has 3 different outputs: semantic segmentation, box mask and box coordinates. When my model is training, the loss of ...
0
votes
0answers
14 views

Maximum and Minimum filters in a Convolution Layer

I’m trying to figure out how to write an optimal convolutional neural network with respect to maximizing and minimizing filters in a Convolution2D layer. This is my thinking and I’m not sure if its ...
1
vote
0answers
7 views

Standardize images using ImageDataGenerator in keras

I was trying to normalize my input data images for feeding to my convolutional neural network and wanted to use standardize my input data. I referred to this article: https://stackoverflow.com/...
2
votes
0answers
21 views

How to detect vanishing gradients in tensorboard?

I have two "sub-questions" 1) How can I detect vanishing or exploding gradients with Tensorboard, given the fact that currently write_grads=True is deprecated in the Tensorboard callback as per "un-...
1
vote
1answer
20 views

Can a NN be configured to indicate which points of the input influenced its prediction and how?

Suppose I want to classify a dataset like the MNIST handwritten dataset, but it has added distractions. For example, here we have a 6 but with extra strokes around it that don't add value. I suppose ...
2
votes
1answer
24 views

Reinforcement-learning: grey-scaling vs color of CNN input. Tradeoff?

I'm doing reinforcement learning and have a visual observation as state input for my agent. In the Deepmind Atari paper they greyscale the input image before they input it into the CNN to reduce the ...
1
vote
0answers
22 views

Weird border artifacts when training a CNN

I've been trying to use this DeepLabv3+ implementation with my dataset (~1000 annotated images of the same box, out of the same video sequence): https://github.com/srihari-humbarwadi/...
0
votes
0answers
8 views

Specifying resolution for objects with known dimensions using CNN

I would like to ask you for advice. I deal with beekeeping but I am also a bit a programmer and an electronics specialist. And this is where my 3 interests come together, actually 4 because recently ...
1
vote
1answer
26 views

Can I provide a CNN with hints?

Let's say I want to classify a dataset of handwritten digits (CNNs on their own can get 99.7% on the MNIST dataset but let's pretend they can only get 90% for the sake of this question). Now, I ...
1
vote
0answers
33 views

Can neural style transfer work on the image style in this question or is there a better technique?

I've been working with this neural style paper https://arxiv.org/pdf/1508.06576v2.pdf to try and transfer the style from this image to photos of pets. In case you're not familiar with the technique, I'...
0
votes
0answers
9 views

Conv-2 CNN architecture - CIFAR-10

I have a CNN architecture for CIFAR-10 dataset which is as follows: Convolutions: 64, 64, pool Fully Connected Layers: 256, 256, 10 Batch size: 60 Optimizer: ...
1
vote
1answer
28 views

How do I generate a feature representation of a saliency map (or mask)?

Generally, CNNs are used to extract feature representations of an image. I'm right now dealing with the class of CNN that produces saliency maps, which are generally in the format of a mask. I'm ...
0
votes
0answers
6 views

How does the BERT model (in Tensorflow or Paddle-paddle frameworks) relate to nodes of the underlying neural-net that's being trained?

The BERT model in frameworks like TensorFlow/Paddle-paddle shows various kinds of computation nodes (like subtract, accumulate, add, mult etc) in a graph like form in 12 layers. But this graph doesn'...
0
votes
0answers
10 views

Exhaustive Nearest Neighbor Search vs KNN

I have two lists of feature vectors calculated from pre-trained CNN for image retrieval task: Query: FV_Q and Reference FV_R. <...
0
votes
0answers
21 views

Autoencoder symmetry

I'm building Autoencoder. In the encoding part I use several strided and diluted convolutions per stage of encoding but I'm wondering if I have to construct the decoding part in a symmetric way. My ...
0
votes
0answers
18 views

What is the use of concatenate layer in CNN?

I am not asking what does concatenate layer does in general in point of mathematical operation. But at feature level, what significance does it provide. Does it helps removing false negatives or does ...
3
votes
1answer
32 views

How to solve the problem of variable-sized AST as input for a (convolutional) neural network model?

In my work I have a given source code for a module. From this module I generate an AST, whose size is dependent on the size of the module (e.g. more source code -> bigger AST). I want to train a ...
0
votes
0answers
23 views

Why would my neural network run faster on my laptop than on my university's supercomputer?

I am trying to get my neural network running on my university's supercomputer in order to decrease its runtime (not for training, for testing - feedforward runs only). However, the Matlab function I ...
0
votes
0answers
7 views

How to perform PGD on a pretrained CNN?

I have a pretrained CNN model using the keras library. I now need to perform a Projected Gradient Descent (PGD) to develop some adversarial examples. To do this, I will need to perform a gradient ...
1
vote
1answer
24 views

Hand-Signs Recognition using Deep Learning Convolutional Neural Networks

I am developing a CNN model to recognize 24 hand-signs of American Sign Language. I have 2500 Images/hand-sign. The data split is: Training = 1250 Images/hand-sign Validation = 625 Images/hand-sign ...
0
votes
1answer
16 views

Positive bias causes the calculation of incorrect gradients

I have a data set with a positive bias (an image, where the values range from 0 to 1), that seems to be causing my network to calculate incorrect gradients. If I just use the raw image as input, of ...
1
vote
1answer
45 views

Are there names for neural networks with a well-defined layer or neuron characteristics?

Are there names for neural networks with a well-defined layer or neuron characteristics? For example, a matrix that has the same number of rows and columns is called a square matrix. Is there an ...
0
votes
2answers
16 views

Binarize ConvNet Feature vector

Given a pre-trained CNN model, I extract feature vector of 3450 reference images FV_R as follows: ...
1
vote
1answer
55 views

Is a non-linear activation function needed if we perform max-pooling after the convolution layer?

Is there any need to use a non-linear activation function (ReLU, LeakyReLU, Sigmoid, etc.) if the result of the convolution layer is passed through the sliding window max function, like max-pooling, ...
0
votes
0answers
21 views

Web stream requests prediction architecture

What's in your opinion the best possible architecture for the following problem ? If you have any code that can be used it would be great . Dataset : 400.000 samples given in hex format in an .xlsx ...
2
votes
1answer
25 views

How to represent and work with the feature matrix for graph convolutional network (GCN) if the number of features for each node is different?

I have a question regarding features representation for graph convolutional neural network. For my case, all nodes have a different number of features, and for now, I don't really understand how ...
0
votes
0answers
17 views

Padding all non-square input image matrices dynamically in a training set

I have input images of dimensions (16,8) which obviously aren't square matrices. I am training this dataset on a CNN. I want to pad zeroes using tf.pad() so that ...
1
vote
1answer
18 views

Interpolating image to increase resolution before feeding it to a neural network

Interpolation is a common way to make an image fit the right input shape for a neural network. But is there any point in using interpolation to make it easier for the network to learn? I assume ...
3
votes
2answers
65 views

When is max pooling exactly applied in convolutional neural networks?

When using convolutional networks on images with multiple channels, do we max pool after we sum the feature map from each channel, or do we max pool each feature map separately and then sum? What's ...
0
votes
1answer
29 views

Best architecture to learn image rotation?

Given an input image and an angle I want the output to be the image rotated at the given angle. So I want to train a neural network to do this from scratch. What sort of archetecture do you think ...
1
vote
0answers
12 views

Acoustic Input Data: Decibel or Pascals

In acoustics decibel levels were defined to solve an issue with showing values that are interpretive, understandable, and easy to communicate in contrast to intensity or pressure in Pascals. $dB = ...
0
votes
1answer
17 views

Convert input dataset given in hex addresses to int

I have created an LSTM Neural Network which take as input the following format in an .csv file ...
1
vote
1answer
54 views

Possible model to use to find pixel locations of objects

I want to make a model that outputs the centre pixel of objects appearing in an image. My current method involves using a CNN with L2 loss to output an image of equivalent size to the input where ...
1
vote
1answer
51 views

How is the depth of filters of hidden layers determined?

I am a bit confused on the layer depth of later convolutional filters. At layer 1 there are usually 40 or so 3x3x3 filters. Each of these filters outputs a 2d array so the total output of the first ...
0
votes
0answers
24 views

How would I go about performing a single step of gradient descent on this model?

I have a classification model that consists of a CNN followed by an SVM. I used the Keras library for the CNN portion and sklearn for the SVM portion. I am assuming I will have to fiddle with the ...
1
vote
0answers
23 views

Why does the BatchNormalization layer produce different outputs during training and inference?

I modified resnet50 architecture to get a regression network. I just add batchnorm1d and ReLU layers just before the fully connected layer. During the training, the output of batchnorm1d layer is ...
1
vote
0answers
14 views

Transpose convolution in TiF-GAN: How does “same” padding works?

This question should be quite generic but I faced the problem in the case of the TiF-GAN generator so I am going to use it as an example. (Link to paper) If you check the penultimate page in the ...
1
vote
0answers
10 views

Text detection on English and Chinese language

https://arxiv.org/abs/1910.07954 In this paper, we have a convolutional character neural network where we have object detection by taking a character as a basic unit. First, we do character detection ...
1
vote
0answers
24 views

What is the difference between using a backbone architecture and transfer learning?

I'm super new to deep learning and computer vision, so this question may sound dumb. In this link (https://github.com/GeorgeSeif/Semantic-Segmentation-Suite), there are pre-trained models (e.g., ...
2
votes
1answer
45 views

Can a neural network learn to predict a number given a binarized image of a rectangle?

Let's assume that we have a regression problem. Our input is just binarized image that contains a single rectangle and we want to predict just a float number. Actually, this floating-point number ...
29
votes
6answers
9k views

Why do CNN's sometimes make highly confident mistakes, and how can one combat this problem?

I trained a simple CNN on the MNIST database of handwritten digits to 99% accuracy. I'm feeding in a bunch of handwritten digits, and non-digits from a document. I want the CNN to report errors, so I ...
1
vote
1answer
58 views

Param count in last layer high, how can I decrease?

Not sure where to put this... I am trying to create a convolutional architecture for a DQN in keras, and I want to know why my param count is so high for my last layer compared to the rest of the ...
1
vote
1answer
78 views

How many layers exists in my neural network?

I have a neural network model defined as below. How many layers exist there? Not sure which ones to count when we are asked about the number. ...
2
votes
1answer
43 views

What make a CNN suitable for image classification or for semantic segmentation?

I've just started with CNN and there is something that I haven't understood yet: How do you "ask" a network: "classify me these images" or "do semantic segmentation"? I think it must be something on ...
1
vote
0answers
17 views

How can we combine different deep learning models?

I know that ensembles can be made by combining sklearn models with a VotingClassifier, but is it possible to combine different deep learning models? Will I have to make something similar to Voting ...
1
vote
0answers
19 views

Efficient implementation of seperable convolution in tensorflow [closed]

It seems like the native implementation of separable convolution in tensorflow is not efficient. https://github.com/tensorflow/tensorflow/issues/12940 Is anyone aware how can we get an efficient ...
1
vote
0answers
4 views

What is generally the best way to combine tabular image metadata with image data in a convolutional neural network?

I have 26 features from tabular data (clinical variables from patients like age gender etc) that I want to add to my cnn which is using xray images from patients. I am using the inception network. ...
2
votes
1answer
41 views

What are examples of approaches to dimensionality reduction of feature vectors?

Given a pre-trained CNN model, I extract feature vector of images in reference and query dataset with several thousands of elements. I would like to apply some augmentation techniques to reduce the ...
1
vote
1answer
31 views

Where can I upload a large photo database for public access? [closed]

I am applying for a grant, and one of the tasks we are seeking funding for is to make a large image database publicly available for users to train artificial intelligence (convolutional neural network)...

1 2 3 4 5 13