From 5d7af97981ecc794fc1988c4916462fcc7b1aa22 Mon Sep 17 00:00:00 2001 From: Ross Wightman Date: Thu, 5 Dec 2019 11:47:57 -0800 Subject: [PATCH] Update README.md Update latest training hparam/command line with correct RandAugment config string (`noise` -> `mstd`) --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 6f3f4410..33b61779 100644 --- a/README.md +++ b/README.md @@ -5,7 +5,7 @@ ### Dec 4, 2019 * Added weights from the first training from scratch of an EfficientNet (B2) with my new RandAugment implementation. Much better than my previous B2 and very close to the official AdvProp ones (80.4 top-1, 95.08 top-5). - * For those interested in hparams, I trained with the following: `./distributed_train.sh 2 /imagenet/ --model efficientnet_b2 -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.3 --drop-connect 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-noise0.5 --remode pixel --reprob 0.2 --amp --lr .016` + * For those interested in hparams, I trained with the following: `./distributed_train.sh 2 /imagenet/ --model efficientnet_b2 -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.3 --drop-connect 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .016` ### Nov 29, 2019 * Brought EfficientNet and MobileNetV3 up to date with my https://github.com/rwightman/gen-efficientnet-pytorch code. Torchscript and ONNX export compat excluded.