Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [image-classification]

For questions about image classification: a decision problem where an algorithm must decide to which class ('cat', 'chair', 'tree') an input image belongs.

732 questions
41
votes
2 answers

How to prepare/augment images for neural network?

I would like to use a neural network for image classification. I'll start with pre-trained CaffeNet and train it for my application. How should I prepare the input images? In this case, all the images are of the same object but with variations…
Alex I
  • 3,152
  • 1
  • 23
  • 27
23
votes
8 answers

Rationale behind most published works in medical imaging trying to reduce false positives

In medical image processing, most of the published works try to reduce false positive rate (FPR) while in reality, false negatives are more dangerous than false positives. What is the rationale behind it?
Hunar
  • 1,197
  • 2
  • 11
  • 33
23
votes
4 answers

What is the difference between Inception v2 and Inception v3?

The paper Going deeper with convolutions describes GoogleNet which contains the original inception modules: The change to inception v2 was that they replaced the 5x5 convolutions by two successive 3x3 convolutions and applied pooling: What is the…
Martin Thoma
  • 19,540
  • 36
  • 98
  • 170
21
votes
3 answers

Image resizing and padding for CNN

I want to train a CNN for image recognition. Images for training have not fixed size. I want the input size for the CNN to be 50x100 (height x width), for example. When I resize some small sized images (for example 32x32) to input size, the content…
Odgiiv
  • 333
  • 1
  • 2
  • 7
21
votes
4 answers

How to maximize recall?

I'm a little bit new to machine learning. I am using a neural network to classify images. There are two possible classes. I am using a Sigmoid activation at the last layer so the scores of images are between 0 to 1. I expected the scores to be…
Louis
  • 404
  • 1
  • 4
  • 12
21
votes
6 answers

Tool to label images for classification

Can anyone recommend a tool to quickly label several hundred images as an input for classification? I have ~500 microscopy images of cells. I would like to assign categories such as 'healthy', 'dead', 'sick' manually for a training set and save…
jlarsch
  • 401
  • 1
  • 3
  • 8
18
votes
2 answers

How many images per class are sufficient for training a CNN

I'm starting a project where the task is to identify sneaker types from images. I'm currently reading into TensorFlow and Torch implementations. My question is: how many images per class are required to reach a reasonable classification…
Feynman27
  • 301
  • 1
  • 2
  • 5
17
votes
2 answers

Updating the weights of the filters in a CNN

I am currently trying to understand the architecture of a CNN. I understand the convolution, the ReLU layer, pooling layer, and fully connected layer. However, I am still confused about the weights. In a normal neural network, each neuron has its…
Felix
  • 173
  • 1
  • 1
  • 5
15
votes
3 answers

Is there a person class in ImageNet? Are there any classes related to humans?

If I look at one of the many sources for the Imagenet classes on the Internet I cannot find a single class related to human beings (and no, harvestman is not someone who harvests, but it's what I knew as a daddy longlegs, a kind of spider :-). How…
DeltaIV
  • 399
  • 1
  • 3
  • 14
13
votes
2 answers

Finding outliers in Image dataset

I have been working on an image classification tasks for which I am extracting the image frames from the video stream collected for different classes. I have already trained an image classification model (using transfer learning) however due to the…
deepguy
  • 1,471
  • 8
  • 21
  • 39
13
votes
1 answer

Reason for square images in deep learning

Most of the advanced deep learning models like VGG, ResNet, etc. require square images as input, usually with a pixel size of $224x224$. Is there a reason why the input has to be of equal shape, or can I build a convnet model with say $100x200$ as…
spore234
  • 613
  • 8
  • 14
12
votes
2 answers

Have 100% images from ImageNet been proven to belong to the class annotated?

Is it proven that all 15M images were manually classified correctly and there are no mistakes or randomly selected responses collected?
ivan866
  • 220
  • 2
  • 7
11
votes
5 answers

Covariate shift detection

Is there any standard approach for detecting the covariate shift between the training and test data ? This would be useful to validate the assumption that covariate shift exists in my database which contains a few hundred images.
Daniel Wonglee
  • 191
  • 1
  • 4
11
votes
1 answer

Data preprocessing: Should we normalise images pixel-wise?

Let me present you with a toy example and a reasoning on image normalisation I had: Suppose we have a CNN architecture to classify NxN grayscale images in two categories. Pixel values range from 0 (black) to 255 (white). Class 0: Images that…
lucasrodesg
  • 235
  • 2
  • 7
11
votes
3 answers

ReLU vs sigmoid in mnist example

PLEASE NOTE: I am not trying to improve on the following example. I know you can get over 99% accuracy. The whole code is in the question. When I tried this simple code I get around 95% accuracy, if I simply change the activation function from…
user
  • 2,023
  • 7
  • 23
  • 38
1
2 3
…
48 49