Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [convnet]

For questions regarding "Convolutional Neural Networks" (CNN)

1
vote
0answers
35 views

What is the best architecture for Auto-Encoder for image reconstruction?

I am trying to use Convultional Auto-Encoder for its latent space (embedding layer), specifically, I want to use the embedding for K-nearest neighbor search in the latent space (similar idea to ...
1
vote
1answer
24 views

Accuracy improving but, val_acc oscillating in ConvNet. What does it mean?

In my ConvNet model, i'm trying to classify some images. It is malware images and it doesn't contain complex features (i think), as expected model learn to classify images easily. You can see my ...
2
votes
1answer
139 views

What is fractionally-strided convolution layer?

In paper Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs, in Section 3.4, it said Since, the aim of this work is to estimate high-resolution and high-quality density maps,...
1
vote
0answers
16 views

Character segmentation using deep learning

I'm developing a character segmentation algorithm for license plate OCR. My algorithm includes two steps: segmentation and recognition. There is almost no problem for recognition thanks to CNN. My ...
1
vote
1answer
21 views

Why can't I use data augmentation with a pretrained convnet?

Reading Deep Learning with Python by François Chollet. In section 5.3.1, we've instantiated a pretrained convnet, VGG16, and are given two options to proceed: A) Running the convolutional base over ...
0
votes
0answers
28 views

Dimension of feature vectors for classification task in the DCGAN paper

I am trying to implement one of the section in the DCGAN paper (https://arxiv.org/pdf/1511.06434.pdf) i.e. Using the Discriminator network trained on ImageNet-1k as a feature extractor to classify ...
1
vote
0answers
17 views

Paper about AE-CNN is unclear. Deriving layers of dense blocks?

I am implementing the algorithm called Automatically Evolving CNN (AE-CNN). Some things aren't specified which makes it a bit hard to understand what the paper actually means to say. In the chapter 3....
0
votes
0answers
10 views

How to custom build a convolution generator network?

I learned GAN's by using mnist dataset(28x28) and codes available in the web. Now I am trying to build a GAN for dataset with images containing custom channel, rows, columns. eg:(3,300,200). I have ...
0
votes
1answer
10 views

Setting input shape for an NLP task in R(Rstudio) using keras 1D convolution layer, when it expects 3 dimensional input (a tensor)

I am using R programming language and using Keras API to build a functional 1D CNN. I have a matrix of my dataset of the following shape rows*features (6000*1024). The input layer is set using the ...
0
votes
0answers
16 views

CNN: Should I include null examples in the training set for image segmentation

I am new to CNNs and was trying to use the Spacenet Building footprints data for some semantic image segmentation. However, in looking at the training images I found that a large number of images have ...
0
votes
0answers
27 views

Overfit problem in siamese network with triplet loss

I have built a siamese network which uses triplet loss for heterogeneous face recognition system. I have created $40000$ triplets from $20$ subject each of them has $5$ anchors. Also note that I am ...
0
votes
0answers
18 views

Yolo-v3 tiny *.weights file contains less weights then expected

I have builded a Yolo V3 Tiny model in Tensorflow and I would like to load the weights provided by Yolo itself. I found here and reading the official Yolo code, that I can read yolov3-tiny.weights ...
0
votes
0answers
62 views

Understanding How to Shape Data for ConvLSTM2D in Keras

Data: I have a spatio-temporal dataset which is approximately 5 years worth of crime data for New York City. This has been aggregated into a space-time grid so that the three dimensions of the matrix ...
0
votes
0answers
40 views

CNN saliency maps for regression problems

I've been using CNNs for regression tasks. While I know there are techniques such as integrated gradients and guided backpropogation to generate saliency maps, most examples generate saliency maps ...
0
votes
1answer
21 views

Weighted samples in Tensorflow for convolutional neural networks

For my binary classification problem (A vs B), each image in either class has its individual weight. This means, for example, if I have 10000 images for A, not all of the images are equally important....
1
vote
0answers
87 views

Multi label classification and sigmoid function

I'm new to neural networks so this may be silly question. I have build standard CNN network for image classification. I want multi-label classification network so I use binary_crossentropy as loss ...
0
votes
1answer
50 views

Application of Deep Reinforcement Learning

I'm new to deep learning, and especially to reinforcement learning. I would like to know if it's possible to predict which combination of hashtags (from a subset of chosen hashtags) would produce the ...
0
votes
1answer
39 views

Conv bias or not with Instance Normalization?

It is well known that Conv layers that are followed by BatchNorm ones should not have bias due to BatchNorm having a bias term. Using InstanceNorm however, the statistics are instance-specific rather ...
0
votes
0answers
44 views

Siamese network using VGG16 to verify the similarity images

I want to create a deep learning model which verify the similarity of the images. So, I will use Siamese network. My dataset is images dataset not CSV file. How can I create a Siamese network using ...
4
votes
1answer
43 views

CNN computing time on good CPU vs cheap GPU

I am a researcher working on my first deep learning project, which consists of using a CNN (pre-trained VGG16+2 densely connected layers) to classify drone imagery of vegetation. In trying to hack ...
0
votes
0answers
20 views

Equivariant Representation in CNN

When I was looking through the internet about the explanation of equivariant representation, I found out that a function is said to be equivariant if and only if g[f(x)] = f(h[x]), where g and h are ...
2
votes
0answers
93 views

1x1 convolutions, equivalence with fully connected layer

I'm confused by the concept of equating a 1x1 convolution with a fully connected layer. Take the following simple example of a 1x1 convolution of 2 input channels each of size 2x2, and a single output ...
1
vote
0answers
14 views

Supervisory information through side output in convolutional neural network

I am trying to implement this paper https://ieeexplore.ieee.org/document/7828014 Here they have mentioned text local (edge) and global regions as supervisory information. Side output is generated ...
0
votes
0answers
18 views

Can we do convolutions on binary mask inputs?

I am training a vehicle trajectory prediction algorithm using Deep MaxEnt Inverse Reinforcement Learning (https://arxiv.org/abs/1507.04888). My intention is to have as input to this algorithm a top-...
1
vote
1answer
26 views

Can I use the Softmax function with a binary classification in deep learning?

I want to create a deep learning model (CNN) for binary classification, can I used the softmax function instead of the sigmoid function in binary classification? Adding the classification layer to ...
0
votes
0answers
55 views

How to project a bounding box on feature map?

I'm trying to implement a custom ROI pooling layer in Keras. According to the Fast-RCNN publication, ROI pooling is done this way: RoI max pooling works by dividing the $h \times w$ RoI window into ...
0
votes
0answers
44 views

LeNet-5 - combining feature maps in C3 layer

Famous LeNet-5 architecture looks like this: The output of layer S2 has dimension: 10x10x6 - so basically an image with 6 convultions applied to it to derive features. If each dimension was again ...
0
votes
0answers
26 views

How to train two neural networks together

This could be considered as an extension of my previous question "How to make a region of interest proposal from convolutional feature maps?". Network 1: I have a multi-input neural network, it ...
1
vote
2answers
152 views

Can pooling ever increase accuracy in convolutional neural networks?

In ConvNets, pooling is used to downsize the input volume, leading to fewer parameters, leading to computational efficiency and possibly helping with overfitting. But can pooling ever increase the ...
1
vote
1answer
58 views

How to make a region of interest proposal from convolutional feature maps?

Problem Keras does not have any direct implementation of region of interest pooling. I am aware of how to perform maxpooling, but I don't know how to get bounding boxes from feature maps passed from ...
0
votes
0answers
14 views

Creating an image data set from a set of 2D points?

I have N sets of x and their corresponding y coordinates. e.g. x_i = [1.1, 2.3, 3.5] & y_i = [-1.1, -3.2, -5.2]. These coordinates represent an image, which may belong to one of two classes. I ...
1
vote
1answer
34 views

What is exactly meant by neural network that can take different types of input?

There is a scientific document that implements a convolutional neural network to classify 3 different types of data, although how exactly, is unknown to me. Here's the explanation of network ...
1
vote
0answers
36 views

Make image label prediction from Chainer CNN model

I have train dataset of 8000 images and labels. Validation set consists of 1957 images and labels. The test set contains 2487 images. Each image contains White Blood Cell images. WBC is divided innto ...
0
votes
1answer
21 views

Generated training set on convnet

I have a dataset with roughly 800 images that are classified in 18 classes. The classes are spread unevenly, with some classes having 30 images and others having 5. In order to increase my dataset,...
3
votes
1answer
53 views

Does it make sense to train a convolutional neural network on lo-res, use on hi-res pictures?

this is my first machine learning project and actually also my first question here. I am a novice to machine learning with a background in theoretical physics. I want to use a CNN to detect scratches ...
1
vote
1answer
125 views

What features are extracted from pre-trained model of CNN Keras?

I would like to use the CNN pre-trained model in feature extraction but I don't know what features are extracted from that. Please let me know!
0
votes
0answers
23 views

Dataset for GANs (logo generation)

I'm begining work on a new project that involves GANs. So far what I've learnt from some publications (e.g. this) is that these models require literally tonnes of images, e.g. 80K. The problem I'm ...
2
votes
1answer
36 views

Are there real world applications where deep fully connected networks are better suited than ConvNets

I would like to give some brief background for my question to avoid answers that explain the difference between fully connected nets and ConvNets. I completed the first 3 courses in the deep learning ...
0
votes
1answer
103 views

Difference between 1x1 Convolution and TimeDistributed(Dense())

Are these lines of code equivalent in Keras? From a few runs, they seem to be, and also intuitively since the channels dimension of my data is 1, my understanding is that a fully connected acts like a ...
1
vote
1answer
30 views

Performance of CNN based deep models with number of classes

How does a given deep cnn model performance vary with number of classes in tasks such as classification, object detection segmentation? For example mobilenet v2 gives around 90% accuracy on ...
0
votes
1answer
23 views

Wrangling data for CNN

I am using convolutional nets for a physics application. I am trying to figure out how to structure my raw data as an image for input into the CNN. I have $N$ samples. Each sample consists of the ...
3
votes
0answers
32 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 ...
1
vote
1answer
140 views

Question about “1x3 and 3x1 conv is equivalent to 3x3 conv”

I see a lot of sites talk that we can substitute 1x3 conv + 3x1 conv for 3x3 conv. In order to demonstrate easily, we use a 3x3 image as an example. From the point of view of parameters, I know that ...
5
votes
4answers
75 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 ...
1
vote
1answer
29 views

How would you a apply a cnn to do age estimation on static images? [closed]

After doing some reading on age estimation using the IMDB wiki dataset I wanted to try it out myself on a smaller scale but I dont quite understand the application of the CNN. Any clarification would ...
0
votes
0answers
11 views

What kind of layer can do a channel number reduction?

I have a tensor of (1, 1, 1000, 64), i.e. a vector of 1x1000 with depth=64 channels. I'd like to transform this into a vector with a single channel (1, 1, 1000, 1): Using: a ...
0
votes
1answer
162 views

How to increase accuracy of model from tensorflow model zoo?

Situation: My dataset is 70k images of people wearing clothes. Images are labeled: bbox position and class. There are 10 classes. I did 80:20 split. Categories are balanced with exception of one ...
1
vote
1answer
53 views

How can I create a pixel labelled image for Semantic Segmentation?

I am following the Semantic Segmentation Examples tutorial by MathWorks. I understand that I can load pixel labeled images ...
1
vote
1answer
206 views

CNN backpropagation between layers

I have this CNN architecture: I know how to calculate error for weights based on the output and update weights between output<-->hidden and hidden<-->input layers. The problem is that I have ...
1
vote
2answers
47 views

Subsequent convolution layers

Note: I've read How do subsequent convolution layers work? a few times, but it's still difficult to understand because of the parameters $k_1$, $k_2$, and many proposals (1, 2.1, 2.2) in the question. ...