This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
news:the_infinite_mnist_dataset [2014/12/18 22:18] leonb |
news:the_infinite_mnist_dataset [2018/05/24 10:50] (current) leonb |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| ====== The infinite MNIST dataset ====== | ====== The infinite MNIST dataset ====== | ||
| - | {{five.png?150 }} | + | {{ five.png?120}} |
| Why settle for 60000 MNIST training examples when you can have [[: | Why settle for 60000 MNIST training examples when you can have [[: | ||
| - | |||
| The MNIST8M dataset was generated using the elastic deformation code originally written | The MNIST8M dataset was generated using the elastic deformation code originally written | ||
| 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 have repackaged the generation code in | Instead of regenerating the files, I have repackaged the generation code in | ||
| - | a 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 [[: | ||