This dataset is made up of 1797 8x8 images. Each image, like the one shown below, is of a hand-written digit. In order to utilize an 8x8 figure like this, we’d have to first transform it into a feature vector with length 64 link.
- See here for more information about this dataset.
- Python 3.7 64bit
- Get the package from PyPi :
- All requirement that you will need its exist in
requirements.txt
so you just need to run this command :
!pip install -r requirements.txt
- Get EMNIST data :
print(__doc__)
# Code source: Gaël Varoquaux
# Modified for documentation by Jaques Grobler
# License: BSD 3 clause
from sklearn import datasets
import matplotlib.pyplot as plt
#Load the digits dataset
digits = datasets.load_digits()
#Display the first digit
plt.figure(1, figsize=(3, 3))
plt.imshow(digits.images[-1], cmap=plt.cm.gray_r, interpolation='nearest')
plt.show()
Congratulation.
- Open the notebook
digit_recognizer_notebook/main.ipynb
and edit it as you want. - main.ipynb
- El Houcine ES SANHAJI - Initial work - essanhaji