368 Commits

Author	SHA1	Message	Date
Marcel Bischoff	af5a4e0f5a	alternative to einsum which is slow in extreme cases (#44) ... * 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 Co-authored-by: Marcel Bischoff <marcel@Marcels-iMac.local>	2020-11-02 06:36:07 -08:00
George Hotz	e01e35e545	14 ops to write for GPU	2020-10-31 10:59:30 -07:00
George Hotz	06928cf3cc	ENET WORKS	2020-10-31 10:42:58 -07:00
George Hotz	68cba88e8f	fix enet bugs, now is mousetrap	2020-10-31 10:28:07 -07:00
George Hotz	053c319708	optional look at cat	2020-10-30 09:30:15 -07:00
George Hotz	2c7e75d733	group conv: forward pass works (#34) ... * forward pass works * got the backward pass * okay, it's now a coho	2020-10-30 09:19:20 -07:00
George Hotz	71aedc2309	it thinks it's washer. it's cat. bad net. you do bad.	2020-10-30 08:28:05 -07:00
George Hotz	c14473f87d	unit test for batchnorm2d	2020-10-30 08:19:58 -07:00
George Hotz	1dde4ce609	oops, stay in float32	2020-10-29 08:24:12 -07:00
George Hotz	2db670ef26	enet refactor + no sigmoid warning	2020-10-29 08:08:21 -07:00
George Hotz	17fa74c15b	factor out a couple nn ops	2020-10-29 08:01:12 -07:00
George Hotz	cc17e3271a	try to recognize cat. do not succeed	2020-10-27 21:41:52 -07:00
George Hotz	03d9c98f5b	enet work	2020-10-27 21:23:02 -07:00
George Hotz	0ec279951f	enet weight loading	2020-10-27 21:01:48 -07:00
George Hotz	e84ad3e27d	enet runs	2020-10-27 20:16:29 -07:00
George Hotz	9166eb58bb	more enet	2020-10-27 19:37:21 -07:00
George Hotz	41828d768f	sigmoid and more enet	2020-10-27 19:13:47 -07:00
George Hotz	09d1ebcdaa	examples is better	2020-10-27 18:57:00 -07:00