From 20a2be14c3c6c53a2ec9127ea8fc22ba47be5aae Mon Sep 17 00:00:00 2001 From: Ross Wightman Date: Wed, 23 Jun 2021 10:40:30 -0700 Subject: [PATCH] Add gMLP-S weights, 79.6 top-1 --- README.md | 3 +++ timm/models/mlp_mixer.py | 4 +++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 6b41d772..07c71a76 100644 --- a/README.md +++ b/README.md @@ -23,6 +23,9 @@ I'm fortunate to be able to dedicate significant time and money of my own suppor ## What's New +### June 23, 2021 +* Reproduce gMLP model training, `gmlp_s16_224` trained to 79.6 top-1, matching [paper](https://arxiv.org/abs/2105.08050). + ### June 20, 2021 * Release Vision Transformer 'AugReg' weights from [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://arxiv.org/abs/2106.10270) * .npz weight loading support added, can load any of the 50K+ weights from the [AugReg series](https://console.cloud.google.com/storage/browser/vit_models/augreg) diff --git a/timm/models/mlp_mixer.py b/timm/models/mlp_mixer.py index c51e61e3..f128b9c9 100644 --- a/timm/models/mlp_mixer.py +++ b/timm/models/mlp_mixer.py @@ -129,7 +129,9 @@ default_cfgs = dict( mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD), gmlp_ti16_224=_cfg(), - gmlp_s16_224=_cfg(), + gmlp_s16_224=_cfg( + url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/gmlp_s16_224_raa-10536d42.pth', + ), gmlp_b16_224=_cfg(), )