George Hotz 60df954377 Fix weight init: this work? (#391) ...

* this work?

* glorot uniform

* requies_grad broke

* propagate the None correctly

* so this weight init works

* ahh, i think it's this

* can't beat this

* glorot is best for ae

* remove comments

2022-09-25 16:46:33 -04:00

..

yolo

Fix yolo param name (#306)

2022-02-10 01:40:24 -07:00

benchmark_train_efficientnet.py

tinygrad.nn (#367)

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

efficientnet.py

model touchups

2021-11-30 11:13:34 -05:00

mnist_gan.py

tinygrad.nn (#367)

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

serious_mnist.py

Reshape dataset from fetch_mnist (#390)

2022-09-24 21:16:29 -04:00

stable_diffusion.py

Fix weight init: this work? (#391)

2022-09-25 16:46:33 -04:00

train_efficientnet.py

tinygrad.nn (#367)

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

train_resnet.py

tinygrad.nn (#367)

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

transformer.py

tinygrad.nn (#367)

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

vgg7.py

tinygrad.nn (#367)

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

vit.py

support larger ViT models

2021-12-12 10:45:10 -08:00

yolov3.py

Correct spelling mistakes (#314)

2022-04-05 05:22:18 -07:00