Rich E (10) [Avatar] Offline
#1
I'm assuming this is coming, but on page 94, the text says:

In the notebook entitled "<NOTEBOOK NAME>", you'll see a script to pre-process the MNIST dataset and load the rst 1000 images and labels into two numpy matrices called images and labels


Am I missing where this code is? I'd love to take a look at it.
437048 (1) [Avatar] Offline
#2
Yes, I hope you put up a github repo with code and datasets used in the book.
462409 (1) [Avatar] Offline
#3
Did anyone found out the missing code ?
290465 (1) [Avatar] Offline
#4
Yes indeed that would be nice
464945 (2) [Avatar] Offline
#5
Any update on the notebook/the code to read in the MNIST dataset?
464945 (2) [Avatar] Offline
#6
I'm still kind of stuck at this part of the book on how to import and prepare the dataset. Am I missing something, is there any place where I can go to find this notebook? Any help would be very appreciated. Otherwise, the book is really fantastic and fun to work through!
384642 (1) [Avatar] Offline
#7
I've asked him for a copy. Still waiting on it though.

https://twitter.com/iamtrask/status/861971987081691137
15166 (2) [Avatar] Offline
#8
There is a similar project from a couple of years ago here:
https://github.com/makeyourownneuralnetwork/makeyourownneuralnetwork

He makes through 1D network for the MNIST problem here:
https://github.com/makeyourownneuralnetwork/makeyourownneuralnetwork/blob/master/part2_neural_network_mnist_data.ipynb

This shows what happens with the letter '0':
https://github.com/makeyourownneuralnetwork/makeyourownneuralnetwork/blob/master/part2_mnist_data_set.ipynb

The part I had some trouble finding was how the 10 target neurons are set with the correct answers.

He also triggers the network to generate its own idea of a number. This is my major interest- it's the heart of style transfer.
https://github.com/makeyourownneuralnetwork/makeyourownneuralnetwork/blob/master/part3_neural_network_mnist_backquery.ipynb