Yixiang Gao cb5d6576cb cifar step time 65ms while stay above 94% (#1888) ...

* change reduceop heruistics

* add model ema and jit hack

* add ema eval

* have to create a duplicate eval function for jit

* remove manual seed

* 94% achieveable with normal eval

* ema is outputting the same results as normal

* fix ema bug

* ema achieves 94% with fix seed

* multigpu tested

* constant fold decay, fix jit, adjust message for multigpu

* pull SpeedyResNet out of train_cifar()

2023-09-21 11:19:32 +08:00

..

mlperf

[ready] Replacing os with pathlib (#1708)

2023-08-30 10:41:08 -07:00

sovits_helpers

Implementation of SoftVC VITS SVC model (#1371)

2023-08-13 19:43:23 -07:00

vgg7_helpers

[ready] Replacing os with pathlib (#1708)

2023-08-30 10:41:08 -07:00

__init__.py

failing llama test

2023-03-11 16:28:10 -08:00

benchmark_train_efficientnet.py

add cache collector (#1595)

2023-08-28 19:59:55 -07:00

compile_efficientnet.py

[ready] Replacing os with pathlib (#1708)

2023-08-30 10:41:08 -07:00

compile_tensorflow.py

moved extras/jit.py -> tinygrad/jit.py (#599)

2023-02-25 08:32:33 -08:00

efficientnet.py

Fix plt output comment (#1428)

2023-08-03 23:35:52 -07:00

gpt2.py

add seed to gpt-2 (#1869)

2023-09-15 17:34:14 -04:00

hlb_cifar10.py

cifar step time 65ms while stay above 94% (#1888)

2023-09-21 11:19:32 +08:00

index.html

simple exporting models (#1344)

2023-08-01 09:35:48 -07:00

llama.py

Move var_vals from ShapeTracker to LazyBuffer (#1819)

2023-09-08 09:25:10 -07:00

mask_rcnn.py

MaskRCNN Inference (#884)

2023-06-25 15:37:51 -07:00

mnist_gan.py

move state to nn/state (#1619)

2023-08-22 07:36:24 -07:00

serious_mnist.py

move state to nn/state (#1619)

2023-08-22 07:36:24 -07:00

simple_conv_bn.py

move state to nn/state (#1619)

2023-08-22 07:36:24 -07:00

so_vits_svc.py

use class Foo: instead of class Foo(): (#1797)

2023-09-06 12:20:25 -07:00

stable_diffusion.py

patch to remove hack from stable_diffusion.py (#1814)

2023-09-08 09:26:50 -07:00

train_efficientnet.py

move state to nn/state (#1619)

2023-08-22 07:36:24 -07:00

train_resnet.py

move state to nn/state (#1619)

2023-08-22 07:36:24 -07:00

transformer.py

move state to nn/state (#1619)

2023-08-22 07:36:24 -07:00

vgg7.py

[ready] Replacing os with pathlib (#1708)

2023-08-30 10:41:08 -07:00

vit.py

.cpu().numpy() -> .numpy() (#1594)

2023-08-21 09:53:29 -07:00

vits.py

[ready] Replacing os with pathlib (#1708)

2023-08-30 10:41:08 -07:00

whisper.py

[ready] Replacing os with pathlib (#1708)

2023-08-30 10:41:08 -07:00

yolov3.py

.cpu().numpy() -> .numpy() (#1594)

2023-08-21 09:53:29 -07:00

yolov8-onnx.py

[ready] Replacing os with pathlib (#1708)

2023-08-30 10:41:08 -07:00

yolov8.py

use class Foo: instead of class Foo(): (#1797)

2023-09-06 12:20:25 -07:00