From 7622015258a16e2d9291576e98530495b0d2ade6 Mon Sep 17 00:00:00 2001 From: Ross Wightman Date: Sat, 4 Jan 2020 11:51:38 -0800 Subject: [PATCH] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 3d47f6fa..9400e090 100644 --- a/README.md +++ b/README.md @@ -280,9 +280,9 @@ These hparams (or similar) work well for a wide range of ResNet architecture, ge The training of this model started with the same command line as EfficientNet-B2 w/ RA above. After almost three weeks of training the process crashed. The results weren't looking amazing so I resumed the training several times with tweaks to a few params (increase RE prob, decrease rand-aug, increase ema-decay). Nothing looked great. I ended up averaging the best checkpoints from all restarts. The result is mediocre at default res/crop but oddly performs much better with a full image test crop of 1.0. ### EfficientNet-B0 with RandAugment - 77.7 top-1, 95.3 top-5 -Michael Klachko achieved these results with the same command line as for B2, with the recommended B0 dropout rate of 0.2. +Michael Klachko achieved these results with the command line for B2 adapted for larger batch size, with the recommended B0 dropout rate of 0.2. -`./distributed_train.sh 2 /imagenet/ --model efficientnet_b0 -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 0.2 --drop-connect 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .016` +`./distributed_train.sh 2 /imagenet/ --model efficientnet_b0 -b 384 --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 0.2 --drop-connect 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .048` **TODO dig up some more**