mirror of
https://github.com/tinygrad/tinygrad.git
synced 2026-06-13 08:28:55 +08:00
* 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