Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [data-augmentation]

114 questions
11
votes
1 answer

CNN - imbalanced classes, class weights vs data augmentation

I have a dataset with a few strongly imbalanced classes, eg. the smallest class is about 54 times smaller than the largest. Therefore, data augmentation in order to equalize the size of classes seems like a bad idea to me (in the example above each…
I.D.M
  • 175
  • 1
  • 10
7
votes
4 answers

When using Data augmentation is it ok to validate only with the original images?

I'm working on a multi-classification deep learning algorithm and I was getting big over-fitting: My model is supposed to classify sunglasses on 17 different brands, but I only had around 400 images from each brand so I created a folder with data…
Santiago Marin Mejia
  • 73
  • 1
  • 1
  • 4
7
votes
2 answers

Why augmenting the training data with binary attributes works better for our dataset?

We have a dataset with multiple features ~400 where all of the features have a histogram as you can see in the following picture (sampled only a few) Our assumption We thought that this looked like some categorical data where few of the times had a…
George Pligoropoulos
  • 607
  • 3
  • 16
6
votes
1 answer

Why does adding data augmentation decrease training accuracy a tiny bit?

Before data augmentation, my model clearly overfits and hits a 100% training accuracy and a 52% validation accuracy. When only adding data augmentation with Keras, as a regularization technique, it achieves a 95% training accuracy with slower…
Kralley
  • 63
  • 1
  • 3
6
votes
1 answer

Is GridSearchCV in combination with ImageDataGenerator possible and recommendable?

I want to optimize some hyperparameters for a CNN architecture by using GridSearchCV (Scikit-Learn) in combination with Data Augmentation (ImageDataGenerator from Keras). However, GridSearchCV only offers the fit function and not the fit_generator…
Code Now
  • 403
  • 1
  • 6
  • 11
6
votes
2 answers

Data Augmentation for Regression

I want to use deep learning for regression. However, the number of training samples is not large. In image processing, some new samples are generated on the basis of initial data through tasks like rotation to increase the number of data sets. Can I…
Aaron
  • 231
  • 1
  • 3
  • 9
5
votes
1 answer

Memory error on using data generator in keras

I am using the following augmentations on dataset of size 9 GB: datagen = ImageDataGenerator( featurewise_center=False, # set input mean to 0 over the dataset samplewise_center=False, # set each sample mean to 0 …
Srihari
  • 797
  • 4
  • 12
  • 27
5
votes
1 answer

How to implement PCA color augmentation as discussed in AlexNet

I read through "ImageNet Classification with Deep Convolutional Neural Networks" again specifically for details on how to implement PCA color augmentation. I am unsure if I have it right. Here is how I did this in numpy: # original image is…
kawingkelvin
  • 221
  • 1
  • 2
  • 7
5
votes
1 answer

Data Augmentation in videos

I know some techniques for augmenting data when images are used, but I don't know if there are any such techniques specifically catered to videos. Since videos have an additional temporal dimension compared to images I was wondering if there were…
ksh
  • 151
  • 6
4
votes
2 answers

Why are results without Transfer Learning better than with Transfer Learning?

I developed a neural network for license plate recognition and used the EfficientNet architecture (https://keras.io/api/applications/efficientnet/#efficientnetb0-function) with and without pretrained weights on ImageNet and with and without data…
Tobitor
  • 93
  • 9
4
votes
0 answers

Spatial Transformer Networks and Data Augmentation

We are all familiar with the famous Deep Mind paper STN. Upon implementation, such as here, did anyone still use input data augementation such as affine transformations? There are used to make CNN robust to rotation, transformation etc. I wonder how…
Benedict K.
  • 273
  • 1
  • 6
3
votes
0 answers

Is it possible to increase the number of images of one class using data augmentation, which is not applied on the other class, in the same dataset?

I have 2 classes for my image classification problem, say class A and class B, and I am using tensorflow and keras for the same. One of them have around 5K images while the other have just around 2K images. Is it possible to increase the number of…
Hrushikar Teja K
  • 31
  • 4
3
votes
1 answer

First perform data augmentation or normalization?

Should I first perform data augmentation or normalization in deep learning? I am mainly interested in 2D and 3D input data. In tutorials that I have seen so far the data augmentation always comes first. Is there a (mathematical) reason for that?…
Anno
  • 161
  • 1
  • 2
  • 6
3
votes
1 answer

What exactly are the data augmentation experimental Keras' layers doing?

From what I gathered, data augmentation consists in increasing your number of instances in your dataset by applying some transfromations. Let's say I want to classify images. If I apply a random rotation to every image in a data set containing $n$…
CMB
  • 43
  • 4
3
votes
1 answer

How to do data augmentation for Machine Learning on statistical data?

I am training machine learning classification model. I have data in csv format with lets say 5 features(or columns) and 100 such observations(or rows). I want to add more similar data to improve my model accuracy. I do not have more data from…
Mitesh Patel
  • 159
  • 1
  • 4
1
2 3 4 5 6 7 8