Stack Exchange Network

Stack Exchange network consists of 174 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 [conv-neural-network]

Convolutional Neural Networks are a type of neural network in which only subsets of possible connections between layers exist to create overlapping regions. They are commonly used for visual tasks.

0
votes
0answers
15 views

Can a trained neural network recognize rotating characters? [duplicate]

Suppose I have a trained neural network that can recognize, for example numbers from 1 to 10, the size of the picture $28 \times 28$. I made the rotation of these pictures by 90 degrees. Does now ...
0
votes
0answers
14 views

How to use MRI data as an input for a CNN?

I'm trying to train a convolution network for segmenting biomedical images U-net to segment parts of a magnetic resonance image (MRI) reconstruction; a 3D stack of 2D slices. What is the best way to ...
0
votes
1answer
19 views

Am I missing obvious problems with my model

I am using Keras to train a CNN for a single label image classification. The model is being trained on synthesized data and applied to real world images. After a significant amount of trial and error ...
0
votes
0answers
10 views

What does a “similar” dataset mean in the context of fine tuning a CNN?

In https://arxiv.org/pdf/1809.09529.pdf it is said If the new dataset is similar to original dataset, we expect higher-level features in the CNN to be relevant to this dataset. Thus, it is ...
0
votes
1answer
15 views

Data augmentation methods for Raman Spectra

I'm building a CNN model based on Raman spectroscopy data and I wanted to experiment with data augmentation. What would be some reasonable techniques to try? I have found this paper which suggests ...
1
vote
1answer
27 views

How much data is needed to train CNN from scratch?

Any rule of thumb, on how many input images would be needed to have a reasonable chance not to overfit the data when training a CNN from scratch? In other words, what is a reasonable amount of data (...
1
vote
0answers
28 views

Why my validation loss is not converging over multistream model? [closed]

I want to merge two CNNs that are trained over the different dataset. I have taken two sequential models and merged them. But when using customized fit_generator, validation loss is not converging. ...
1
vote
1answer
22 views

Data Augmentation in Keras: How many training observations do I end up with?

I'm reading through Francois Chollet's "Deep Learning with Python" and was recently introduced to a concept I had never encountered before in my statistics studies. Namely, data augmentation. I have a ...
0
votes
0answers
13 views

Interpreting probabilities from image classifier, which model to use?

I'm trying to interpret examples from a probability perspective and my intuition is telling me Logistic Regression should be used for such a purpose despite the score being weaker than the other ...
0
votes
0answers
25 views

How to “use” Yolo Loss Function

I am dealing with Yolo Loss Function (the following). $$\begin{align} &\lambda_{coord} \sum_{i=0}^{S^2}\sum_{j=0}^B \mathbb{1}_{ij}^{obj}[(x_i-\hat{x}_i)^2 + (y_i-\hat{y}_i)^2 ] \\&+ \lambda_{...
0
votes
1answer
47 views

1D CNN for time series regression without pooling layers?

I am working on a prognostics task, where I predict the Remaining Useful Life of some equipment (i.e.: time steps remaining until failure). In order to do that, I use multivariate time series sensor ...
0
votes
0answers
16 views

How do convolutional neural networks deal with many filters during convolution?

I am unsure of how convolutional neural networks treat several filters. Many of the examples I have seen only have filter at a time, and that is intuitive for me. Look at the nice visual tutorial here:...
0
votes
0answers
10 views

Translation invariance of features in convolutional encoder-decoders

A big part of using convolutional layers is translation invariance, i.e., features are detected regardless of their position in the image. In a convolutional encoder-decoder that maps from an image ...
2
votes
0answers
17 views

How should I standardize input when fine-tuning a VGG16 network?

I want to use the VGG16 model pre-trained on ImageNet and fine-tune some layers to my dataset. The VGG16 paper explains their preprocessing steps which I understand to be important to replicate if one ...
1
vote
1answer
31 views

Is it reasonable to use VGG16 with a new fully-connected layer for binary image segmentation?

I am working on binary image segmentation of traffic signs (of which I have RGB images of size 224x224 and accompanying grayscale masks) where I want to classify each pixel as either part of a traffic ...
0
votes
0answers
61 views

What does 1x1 convolution mean in a neural network? (v2)

While studying the architecture of YOLO CNN I saw some 1x1 convolutional layers are included. Trying to understand what they are suppose to be I read this answer. Most of the answers to that ...
0
votes
0answers
8 views

CAM methods for feature visualization in CNNs

One of the major points the authors of CAM insist upon is the ability of Global Average Pooled CNNs to extract features and indentify objects even if they are not specifically trained to do so. By ...
0
votes
1answer
43 views

Whats the difference between a dense layer and an output layer in a CNN?

All deeplearning4j CNN examples I have seen usually have a Dense Layer right after the last convolution or pooling then an Output Layer or a series of Output Layers ...
0
votes
0answers
21 views

Can existing hyperparameters be used when new features are added to data?

Lets say I have a 1D CNN and a dataset on which I have run bayesian optimiztion and I have the best hyperparameters (decided by lowest loss). Now if I decide to add new features to the data, keep the ...
0
votes
0answers
17 views

CNN can't learn - “oscillating” loss function and classifier that marks every sample with same label

I would be really thankful for any hint as I have no idea what to do next. I am trying to create a working convolutional neural network for an image classification task. There is a 96x96 RGB image as ...
1
vote
1answer
31 views

How are inputs to Inception v3 pre-processed?

When using the pre-trained Inception v3 model for image classification, how should the inputs be pre-processed? Should the images be individually normalized to 0 mean, 1 standard deviation? In the ...
0
votes
0answers
32 views

Stack data channels on the input to a CNN?

There are a couple other questions that are similar, but I wanted to be specific. Both this and this talk about adding additional data to a CNN by plugging into the lower layers of the CNN, or using ...
0
votes
3answers
71 views

Using Convolutional Neural Networks on Board Games

I have troubles with my CNN. The code runs and my network learns something, but the performance is really poor. The goal is to play the game Connect 4. The network therefor receives a numpy array with ...
0
votes
1answer
50 views

How are the weights of a CNN computed?

I am trying to understand the logic behind convolutional neural networks. To my understanding, the weights used are nothing more than an $w \times h$ matrix (a filter) and as with the normal neural ...
0
votes
1answer
22 views

Convolutional network - how to choose output channels number, stride and padding?

I am trying to create a convolutional network for image classification problem. I am using PyTorch but I have troubles in understending the implementation of their 2D convolutional layer. I understand ...
1
vote
0answers
29 views

Recommended books about neural networks [closed]

what books do you recommend on neural networks? We can think of a few categories: 1. A python recipe book 2. A general introduction book 3. An Updated book 4. Specialized book on CNNs 5. Specialized ...
0
votes
0answers
17 views

How do deep CNNs handle problem of “perceptual aliasing” while visual place classification?

Deep CNNs have achieved state-of-the-art performance in image classification. The underlying concept of place recognition is similar to image classification where the task is to classify or recognize ...
0
votes
0answers
19 views

Diagonal and horizontal line detection in Convolutional Neural Networks

I have build this CNN model with Keras: ...
0
votes
0answers
28 views

State prediction of how long someone sleeps using neural nets

I have over hundred thousands of datapoints on how long individual people sleep. I also have information about how soft their beds are, their income, stress levels etc. At first I want to predicted ...
0
votes
1answer
29 views

Is convolution in CNNs a similarity measure

Is it correct to say that convolution in CNNs is a similarity measure between filter and receptive field? and what is the difference between correlation and convolution?
0
votes
0answers
35 views

Why is my Semantic Segmentation DL network decreasing in accuracy?

In order to familiarize myself with semantic segmentation and convolutional neural networks I am going through this tutorial by MathWorks: Semantic Segmentation Using Deep Learning I did not use the ...
0
votes
0answers
8 views

Why does the Conv Neural Net using Tensorflow returns same predictions for all the data points [duplicate]

I am predicting usage quantity for different customers across different categories. Following is the network architecture. ...
0
votes
0answers
15 views

How to count people from Multi-column CNN density map?

In this paper, they use Multi-column Convolutional Neural Network (MCNN). The output of MCNN is density map (this is a matrix) and from this density map we can count the number of people. My question ...
0
votes
1answer
84 views

what purpose do the grid cells serve in YOLO object detection algorithm?

so I was looking at YOLO and I read several blogs online, but one concept I'm having trouble understanding is why do we want to divide the image into different grids, and then predict the bounding box ...
0
votes
0answers
54 views

CNN Flower recognition (5 classes) accuracy improvement

I have created a CNN for image recognition (Flower types - 5 classes) and am now considering model parameter changes to improve accuracy. The model (5 3*3conv + 4 2*2max pooling layers) attains ~60% ...
0
votes
0answers
14 views

train loss decreasing and validation didn't [duplicate]

I want to use neural network to disaggregate REDD data, but my train loss is decreasing while validation loss didn't and the results are as follows, can somebody help me, I don't know what to check ...
1
vote
1answer
40 views

How multi layer neural network classify data without extracting features?

In CNN we have convolution layer and pooling layer for feature extraction. How the features are extracted in Fully connected neural network? Secondly CNN has more expressive power and and number of ...
1
vote
1answer
27 views

How can I mix image and data into a CNN

I've recently been testing around tensorflow and keras and I've been doing a project to classify images. So far it's been working but now I want to use real data mixed with the image in order to solve ...
-1
votes
1answer
34 views

Machine learning books covering neural networks / cnn / GAN [duplicate]

I'm not an expert in machine learning. Is there any textbook (with a decent amount of mathematical rigor) that cover the subjects neural network / convolutional neural network / GAN network? I've the ...
2
votes
1answer
24 views

What would happen if CNN reused same kernel weights for each channel?

In a CNN each output location of a feature map is given by the kernel over the previous layer's feature maps. If the receptive field is say 5x5 with 3 channels then there are 5x5x3 weights that are ...
2
votes
1answer
20 views

Clustering / Grouping on image's pixels

I have an image, and im building a model to recognize a pattern in that image and classify it. There is however a lot of noise in the rest of the image, but the actual pattern to classify will always ...
0
votes
0answers
14 views

Different random weight initilization leading to different performances

I'm training a 3D U-Net on an EM dataset of a brain. The objective is to segment neurons in it. During the experiments, I've noticed, different random initialization of the network leads to different ...
0
votes
1answer
39 views

Normalization of inputs in convolutional neural networks

I read that using convolutional neural networks, or any neural networks (?), that the input/features should be normalized. The normalization is typically done for each feature $$x_i \in X \ \ \forall ...
0
votes
0answers
18 views

Batch Normalization and increasing batch size reducing the performance

I'm training a 3D U-Net on an EM dataset of a brain. The objective is to segment neurons in it. During the experiments, I've noticed, increasing batch size, adding batch normalization layers (Conv ->...
3
votes
2answers
56 views

Encoder Decoder networks with varying image sizes

Encoder Decoder Network - Computerphile : At the very beginning of this video, Michael Pound goes on to say: So it (encoder decoder network) makes no assumptions about the size of the input the ...
0
votes
2answers
94 views

convolutional autoencoder on an odd size image

I am trying to apply convolutional autoencdeor on a odd size image. Below is the code: ...
-1
votes
0answers
10 views

Training accuracy of the model keeps decreasing with each epoch even though loss is decreasing

I am training a model to recognise characters from images with 8 conv layers. I am having problem that the train accuracy decreases by large value in each epoch, the first few have like .80-.90, even ...
0
votes
0answers
22 views

U-Net image size for training

I have a small question regarding the size of images used for training the U-Net. I have thus far been able to train a U-Net reasonably well using 656x656 images and now wanted to use sections of ...
0
votes
0answers
10 views

Dropout and feature visualisation

If we use drop out in our CNN, this will lead to features being more displeased and less concentrated on specific neuroma. Won't this make feature visualisation very difficult since we can't locate ...
0
votes
0answers
46 views

Select the right architecture for a deep learning binary classifier on DNA data

I'm working on a deep learning binary classifier. The train dataset properties are: Input matrix : 26500 individuals x 18 000 genes. Genes (SNP) are encoded as follow 0 for homozygous major, 1 for ...