Jacky LeeandGitHub d768acb6a9 Rename Normalize and move to nn (#415) ...

* Rename Normalize and move to nn

* Fix comparison to None error

* Add test for GroupNorm

* Rename test case

* Flip parameters to match PyTorch

* Increase error tolerance

* Fix elementwise_affine on channels

* Match arguments with PyTorch

* Initialize weight and bias only when affine is true

* Is this it?

* A bit cleaner

* Handle case where weight or bias is None

2023-01-25 07:47:59 -08:00

..

llops

cleanups, simple padding in the processing op

2023-01-25 07:37:52 -08:00

nn

Rename Normalize and move to nn (#415)

2023-01-25 07:47:59 -08:00

shape

Typing (#468)

2023-01-21 09:09:22 -08:00

__init__.py

tinygrad.nn (#367)

2022-08-18 07:41:00 -07:00

ast.py

reduce 2.0 (#469)

2023-01-23 15:11:13 -08:00

graph.py

hasattr and DeviceBuffer type fixups

2022-10-28 09:05:45 -07:00

helpers.py

more from indexer

2023-01-18 18:11:51 -08:00

lazy.py

cleanups, simple padding in the processing op

2023-01-25 07:37:52 -08:00

mlops.py

s/contiguous_op/contiguous

2022-11-11 00:07:05 -08:00

ops.py

delete opencl <celebration>

2023-01-24 14:18:35 -08:00

tensor.py

oops, don't assign self

2023-01-09 18:02:12 -08:00