How to create a Image Dataset just like MNIST dataset?

python image-processing dataset neural-network keras
Md Shopon picture Md Shopon · Sep 2, 2016 · Viewed 25k times · Source

I have 10000 BMP images of some handwritten digits. If i want to feed the datas to a neural network what do i need to do ? For MNIST dataset i just had to write

(X_train, y_train), (X_test, y_test) = mnist.load_data()

I am using Keras library in python . How can i create such dataset ?

Answer

Mikael Rousson picture Mikael Rousson · Sep 2, 2016

You can either write a function that loads all your images and stack them into a numpy array if all fits in RAM or use Keras ImageDataGenerator (https://keras.io/preprocessing/image/) which includes a function flow_from_directory. You can find an example here https://gist.github.com/fchollet/0830affa1f7f19fd47b06d4cf89ed44d.

Related questions

Data Augmentation in PyTorch

I am a little bit confused about the data augmentation performed in PyTorch. Now, as far as I know, when we are performing data augmentation, we are KEEPING our original dataset, and then adding other versions of it (Flipping, Cropping...…

Read More
How to resize an image with OpenCV2.0 and Python2.6

I want to use OpenCV2.0 and Python2.6 to show resized images. I used and adopted this example but unfortunately, this code is for OpenCV2.1 and does not seem to be working on 2.0. Here my code: import os, glob import cv …

Read More
How does one convert a grayscale image to RGB in OpenCV (Python)?

I'm learning image processing using OpenCV for a realtime application. I did some thresholding on an image and want to label the contours in green, but they aren't showing up in green because my image is in black and white. …

Read More