Evan Mays 285621aeda Cherry backprop for conv2d (#281) ...

* quick math: 0 + x = x.

* gradient w.r.t. x using cherry for conv

* gradient w.r.t. w for conv on cherry but doing vector dot products

* small optimization

* [cherry] optimize conv backpass for large channel count

* get rid of numpy einsum

2021-10-30 16:12:19 -07:00

..

efficientnet

feat: add efficientnet test (#285)

2021-10-30 15:53:51 -07:00

mnist

Improved __getitem__ (#254)

2021-05-05 22:15:22 -07:00

__init__.py

All devices are equal! (#196)

2020-12-15 23:44:08 -08:00

test_efficientnet.py

feat: add efficientnet test (#285)

2021-10-30 15:53:51 -07:00

test_gc.py

Test split (#231)

2021-01-01 09:19:03 -05:00

test_mnist.py

Improved __getitem__ (#254)

2021-05-05 22:15:22 -07:00

test_net_speed.py

Test split (#231)

2021-01-01 09:19:03 -05:00

test_nn.py

Added ResNet-{18, 34, 50, 101, 152} (#271)

2021-06-21 09:37:24 -07:00

test_ops.py

Cherry backprop for conv2d (#281)

2021-10-30 16:12:19 -07:00

test_optim.py

Test split (#231)

2021-01-01 09:19:03 -05:00

test_tensor.py

Add dropout test (#265)

2021-06-19 08:49:13 -07:00

test_train.py

Added ResNet-{18, 34, 50, 101, 152} (#271)

2021-06-21 09:37:24 -07:00