@Machine_learn
MNIST reborn, restored and expanded.
Now with an extra 50,000 training samples.

If you used the original #MNIST test set more than a few times, chances are your models #overfit the test set. Time to test them on those extra samples.

Now you will use #QMNIST instead of #MNIST
Detailed explanation at #paper: 👇

https://arxiv.org/pdf/1905.10498.pdf

and it's #implementation and some results by using #pytorch: 👇

https://github.com/facebookresearch/qmnist