Marcel Bischoff da72a0eed4 Big MNIST model with PIL augmentation and load/save (#160) ...

* 2serious

* load/save

* fixing GPU

* added DEBUG

* needs BatchNorm or doesn't learn anything

* old file not needed

* added conv biases

* added extra/training.py and checkpoint

* assert in test only

* save

* padding

* num_classes

* checkpoint

* checkpoints for padding

* training was broken

* merge

* rotation augmentation

* more aug

* needs testing

* streamline augment, augment is fast thus bicubic

* tidying up

2020-12-13 20:45:55 -08:00

..

benchmark.py

30 MEGAReLUs. we need to lose 12 lines

2020-12-12 17:07:34 -08:00

efficientnet.py

tinygrad.utils -> extra.utils

2020-12-12 15:26:07 -08:00

mnist_gan.py

Gan is real...Look what tiny just generated! (#192)

2020-12-13 20:23:12 -08:00

serious_mnist.py

Big MNIST model with PIL augmentation and load/save (#160)

2020-12-13 20:45:55 -08:00

train_efficientnet.py

tinygrad.utils -> extra.utils

2020-12-12 15:26:07 -08:00

use_ane.py

30 MEGAReLUs. we need to lose 12 lines

2020-12-12 17:07:34 -08:00