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 [cnn]

Convolutional Neural Networks (CNN, also called ConvNets) are a tool used for classification tasks and image recognition. The name giving first step is the extraction of features from the input data.

0
votes
1answer
18 views

Using Image Data along with CSV file data for CNN model

I have image data along with csv file where each row of csv file contains attributes for corresponding image. I want to use images as well as csv file data to build CNN model using Keras. What is ...
0
votes
1answer
9 views

Preprocessing for finetuned CNN model from pretrained models

Is it necessary to preprocess the images the same way as they were during the training of pretrained models in our finetuned model to use it for a different classification task ? Say, I have a ...
0
votes
1answer
8 views

What architecture would best perform image material segmentation?

I want to perform semantic/stuff segmentation, but then classify and segment with respect to the material properties of objects in an image, rather than the objects themselves. This means that, ...
0
votes
0answers
27 views

Meaning of weights from a 1D convolutional network

just trying to better understand what's happening in my network. I built a 3 layer convolutional network to classify 1D signals. Here it is: ...
0
votes
0answers
16 views

How does fully connected layer predict bounding box in CNN intuitively?

I did a lot of googling,still,don't find a post/article explained this intuitively,especially,how does [x,y,w,h] get?
0
votes
2answers
54 views

Which neural network to choose for classification from text/speech?

I am considering two tasks: Dialog Act Classification from Text (e.g. classify to: question; opinion; ...) Emotion Recognition from Speech (e.g. happy; calm; sad; ...) Which DL model should perform ...
0
votes
1answer
40 views

Why BatchNormalization fails in Keras

I try to test ResNet approach on cifar10 dataset with the following python code: ...
1
vote
1answer
22 views

How does CNN doing bounding box regression and what do features and weights represent for?

I knew that, in the house price logistical regression problem, the weights and features represent the "importance" of factor or coefficients of feature variables respectively, then minimize LSR loss ...
0
votes
1answer
32 views

Keras/TF: Making sure image training data shape is accurate for Time Distributed CNN+LSTM

The comprehensible data shape to me is like: (9186, 120, 120, 1) this means 9186 entry, of 120 by 120 pixel grey images. I learnt that using Time Distributed to design a CNN combined with an LSTM ...
0
votes
0answers
8 views

Spatially encoding textual data

Imagine we have a textual data that must be passed to convolutional neural network. Generally we know that for natural language processing, textual data is embedded into vector space, but in this ...
2
votes
1answer
41 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 ...
2
votes
1answer
49 views

CNN to many outputs

I have a dataset with 100 columns (categorial one-hot encoded) and 1 column with text data (simple sentences) and i want to build a neural network to arround 380.000 outputs labels. I have no idea ...
0
votes
0answers
9 views

Semantic segmentation training on images of different sizes - good practices

What are the good practices of handling images when training the neural networks for semantic segmentation, but the images have different sizes and aspect ratios? Also, how to properly handle small ...
1
vote
0answers
13 views

Generalization of image patches using mean shift?

I'm reading this paper - https://arxiv.org/pdf/1609.04112.pdf and trying to understand the answer to the author's first question - why a nonlinear activation function is essential at the filter ...
0
votes
0answers
6 views

Mapping 4 Dimensional array to predicted output text

Iv been studying machine learning but im struggling with some concepts and cant seem to find particular answers to the question of how theoretical data is mapped into non classification categories. ...
0
votes
1answer
15 views

How can i detect smoke and bluring/filtering using CNN in python

I need some help to make an CNN via python to detection of fire-smoke and make the fire-smoke blur what should I do where can I start some help please.
0
votes
1answer
17 views

inputs and outputs of a fully connected layer for a note classifier

i'm trying to make an object classifier of different musical note types and I'm having a problem understanding fully connected layers. for example I have a 3d array of binarized images (WxLxNo....
0
votes
1answer
26 views

Uniformity of color and texture in an image

I am new to the field of deep learning and have a problem in determining whether two images have uniform color and texture. For example, I have a Master image - Now, with respect to this image i ...
0
votes
0answers
11 views

Fast Style Transfer memory usage

I'm trying to integrate this tensorflow implementation of fast style transfer with GIMP, the open source image editor. In a few word, the plugin would be a wrapper to the ...
0
votes
0answers
44 views

How can I solve error “allocation exceeds 10 of system memory” on keras?

I made a CNN on Keras with Tensorflow backend, my training set has 144 examples, but each example has size of 3200*101. My CNN is very basic, just for learning, batch_size of 2 (I tried reducing it ...
1
vote
1answer
15 views

Changes in CNN architecture

How can I see whether a CNN layer is overfitting, underfitting or whether the activation function, normalisation requires some changes?
1
vote
1answer
23 views

How does testing a CNN work after training? [closed]

i mean that how CNN know the output probability will lead to following class. i mean that if i train the CNN on the Dog and cat picture or data set so at the end of the know that this probability will ...
0
votes
0answers
6 views

CNN architecture design guidelines when doing multilabel classification of 1K possible “easy” classes

in my problem I am given a website screenshot and I need to detect which logos appear on it (nike, youtube, pepsi etc.). From what I have read, this is usually tackled with template matching. However ...
0
votes
1answer
32 views

What is a suitable Tensorflow model to classify images into foggy/not foggy?

I want to classify photos taken by multiple webcams that are operating in mountainous regions into foggy / not foggy. The photos are in various sizes and were taken under very different light ...
1
vote
0answers
9 views

Strangeness in validation loss between CPU vs GPU when training CNN

I've been training an implementation of Mask R-CNN and it was training very successfully on my CPU but I've just set up my GPU and it is giving some strange results when looking at my validation loss. ...
0
votes
0answers
6 views

How to preprocess stereo audio data for a CNN?

I'm working on a deep learning project that whose data consists of stereo wav files where differences between the left and right channel are important. From the research I've done, [mel]spectrograms ...
1
vote
0answers
30 views

Cannot interpret feed_dict key as Tensor: Tensor Tensor(“Placeholder:0”, shape=(3, 3, 3, 32), dtype=float32) is not an element of this graph

I have a working Keras model that makes predictions great in the repl but fails to load in a Flask app on accessing multiple times.. K.clear_session() and graph = tf.get_default_graph() did not work ...
0
votes
2answers
33 views

what happens to the depth channels when convolved by multiple filters in a cnn (keras, tensorflow)

I have a $15$-channel time series that I want to convolve using a $1$d CNN ($1\times n$ time-steps kernel). Now, let's say I want to have, as my first layer, $16$ filters. This would imply to my mind ...
1
vote
1answer
15 views

How to add more emphasis on end columns in CNN?

I am using CNN for multivariate time series analysis. The input size is (batch_size, 500, 30) i.e 30 variables and 500 time steps. I want to put more emphasis on recent data and less on past data. ...
0
votes
1answer
18 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 ...
0
votes
0answers
32 views

Why is YOLO a regression problem solving method?

I am trying to read and understand the YOLO paper and I came across these lines. We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to ...
2
votes
2answers
46 views

Keras Attention Guided CNN problem

I am working on a CNN for XRay image classification and I can't seem to be able to properly train it. I am trying to implement the following paper in Keras: https://arxiv.org/pdf/1801.09927.pdf In ...
2
votes
2answers
45 views

Running out of memory while processing csv file data

I'm getting an error while processing 0.2 million of text data. I'm using CNN text classification in tensorflow. Output raw data shape is 204177x22000. while passing to numpy.array(out_raw), here it ...
1
vote
0answers
28 views

Understanding how to use ConvLSTM for multistep ahead forecasting

I have a problem where I have transaction data for many banking accounts. The task is to train a model on historical debit/expense transactions and then forecast expense transactions for the next n ...
3
votes
2answers
103 views

Tensorflow (or Keras) vs. Pytorch vs. some other ML library for implementing a CNN [closed]

I am looking into implementing a convolutional neural network for a research problem. I've heard of deep learning libraries like Pytorch and Tensorflow and was hoping to get some additional ...
1
vote
1answer
47 views

How to implement a Fourier Convolution layer in keras?

I'm currently investigating the paper FCNN: Fourier Convolutional Neural Networks. The main contribution of the paper is that CNN training is entirely shifted to the Fourier domain without loss of ...
0
votes
1answer
56 views

Multiple-input multiple-output CNN with custom loss function

I have a set of 2D input arrays $(n\times m)$ namely $A,B,C$ and I have to predict two 2D output arrays namely $d,e$ for which I do have the expected values. You can think of the inputs/outputs as ...
0
votes
1answer
16 views

What are some good design practices for creating/improving a CNN?

Recently I've been working on a mini side project in detecting age off of facial images. Aside from mistakes, I have made decent progress in creating my model. ...
1
vote
2answers
33 views

What are the possible approaches to fixing Overfitting on a CNN?

Currently I am trying to make a cnn that would allow for age detection on facial images. My dataset has the following shape where the images are grayscale. ...
1
vote
2answers
23 views

How would I be able to improve my CNN model (Keras)?

Recently I read a research paper on age detection using facial images. So right now because of that I was trying to see how far I could get by applying a CNN to a dataset of facial images (with their ...
1
vote
1answer
41 views

Can a neural network recognize a letter B as an A if your trained it so?

You have a neural network. And you have, say, pictures of $100,000$ hand-written letters (A-Z). Now you make a typical Training and the neural network will recognize an A as an A, a B as a B, ... Now ...
-1
votes
1answer
17 views

Best framework to detect Emotion

I am slightly greater than a beginner to Data Science. Currently I am trying to build an emotion detection API which will detect emotional state from a short video. I have planned to do it with fast....
3
votes
1answer
49 views

Do CNNs benefit from HDR images?

I have images with 12 bits per color channel which I use for several detection networks (YOLO, RetinaNet, etc.). Can I expect any precision difference between 12 bpp and 8 bpp as network input? Or is ...
0
votes
2answers
18 views

Activation in convolution layer

On a CNN, what is use of using Activation function in convolution layer? Does single weight is used for full matrix or for every pixel or box it may vary?
0
votes
0answers
11 views

Understanding YOLO Loss Function

In the following formulation, if xi and yi represent center of anchor box, shouldnt we have ...
1
vote
1answer
18 views

How to use CNN to build ROC curves

I know we can use SVMs probabilities after predicting validation data in order to build ROC curves. However, for CNNs, I have a binary classification problem and so the sigmoid activation function ...
2
votes
1answer
37 views

Very slow convergence with CNN [closed]

I am new to deep learning. I am working on training an SSD model on a set of small objects. I am using Adam gradient descent for optimization and a large input (800x800), but I seem to only get an ...
1
vote
1answer
27 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
25 views

How to decrease CNN model error (lose) rate

My CNN model trained on ct scan dataset of 8000 samples,the model achieve nearly 90% of accuracy but the loss rate is high the average cost in 50 epochs is about 0.30, I use L2 regularization and ...
2
votes
1answer
31 views

How does Pooling Layer in CNN introduce invariance to other transformations besides translation

Here is a quote from deeplearningbook which I am trying to process. I am not sure what do they mean by this quote, can someone help me understand please? Pooling over spatial regions produces ...