First CONVOLUTION

Following the instructions here: http://deeplearning.net/tutorial/lenet.html#lenet

almost worked without issues. However i had to change the path of the input image and the datatype to 32 bit as my theano installation is configured to use the GPU. Works just fine! Smiley

image

Advertisements

Python Tutorial

To print the current working directory:

import os
print „The current working directory is“, os.getcwd()

To Load an Image:

from PIL import Image

# open random image of dimensions 639×516
path=r’C:\Users\Lukas\Theano\wolfmoon.jpg‘
img = Image.open(path)
# dimensions are (height, width, channel)
img = numpy.asarray(img, dtype=’float64′) / 256.