This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Last revision Both sides next revision | ||
news:the_infinite_mnist_dataset [2014/07/11 19:00] leonb |
news:the_infinite_mnist_dataset [2014/12/18 22:19] leonb |
||
---|---|---|---|
Line 1: | Line 1: | ||
====== The infinite MNIST dataset ====== | ====== The infinite MNIST dataset ====== | ||
+ | {{ five.png? | ||
Why settle for 60000 MNIST training examples when you can have [[: | Why settle for 60000 MNIST training examples when you can have [[: | ||
Line 6: | Line 7: | ||
for [[: | for [[: | ||
original MNIST8M files were accidentally deleted from the NEC servers a couple weeks ago. | original MNIST8M files were accidentally deleted from the NEC servers a couple weeks ago. | ||
- | Instead of regenerating the files, I decided to repackage | + | Instead of regenerating the files, I have repackaged |
- | a more convenient form. You can now generate arbitrary amounts of pseudo-random | + | a convenient form. You can now generate arbitrary amounts of pseudo-random |
MNIST training examples. You can even use this code to generate your training | MNIST training examples. You can even use this code to generate your training | ||
data on the fly. We call this the [[: | data on the fly. We call this the [[: |