Marcel Bischoff c7b7f8ccc8 Backwards ops supporting broadcasting (#118) ...

* streamlined numerical_jacobian

* Got rid of the g loop in Conv2D.forward

* ereased stupid line

* nothing

* no loops in Conv2D forward

* Conv2D backprop improved

* stupid things in examples

* alternative to einsum

* Conv2D backward einsum alternative

* tidying up

* tidied up

* no ravel

* got rid of print

* Update efficientnet.py

* Update efficientnet.py

* Update efficientnet.py

* only tensordot

* 255.0

* whitespace

* aspect ratio error in efficientnet

* noprint

* efficient net wrong strides

* broadcasting for backward ops

* Update ops.py

* Update ops.py

- was wrong

* broadcast test for backward enabled

* function adBC + not summing over already 1 axis

* spacing

Co-authored-by: Marcel Bischoff <marcel@Marcels-iMac.local>

2020-11-15 15:21:10 -08:00

..

test_mnist.py

GPU MaxPool2D.backward(); TinyConvNet train passes (#103)

2020-11-11 07:58:43 -08:00

test_net_speed.py

GPU MaxPool2D.backward(); TinyConvNet train passes (#103)

2020-11-11 07:58:43 -08:00

test_nn.py

unit test for batchnorm2d

2020-10-30 08:19:58 -07:00

test_ops.py

Backwards ops supporting broadcasting (#118)

2020-11-15 15:21:10 -08:00

test_optim.py

efficient version of adam (#20)

2020-10-27 15:54:40 -07:00

test_tensor.py

Add GPU Support! (do not merge yet) (#41)

2020-11-01 07:00:49 -08:00