From 2680ad14bbdfd6a52d5c451c9c55ae4934e6dd04 Mon Sep 17 00:00:00 2001
From: Ross Wightman <rwightman@gmail.com>
Date: Wed, 4 Sep 2019 17:38:59 -0700
Subject: [PATCH] Add Res2Net and DLA to README

---
 README.md              |  4 ++++
 timm/models/res2net.py | 11 -----------
 2 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/README.md b/README.md
index 66cea1d5..f622f51f 100644
--- a/README.md
+++ b/README.md
@@ -25,6 +25,10 @@ I've included a few of my favourite models, but this is not an exhaustive collec
     * ResNet-18, ResNet-34, ResNet-50, ResNet-101, ResNet-152, ResNeXt50 (32x4d), ResNeXt101 (32x4d and 64x4d)
     * 'Bag of Tricks' / Gluon C, D, E, S variations (https://arxiv.org/abs/1812.01187)
     * Instagram trained / ImageNet tuned ResNeXt101-32x8d to 32x48d from from [facebookresearch](https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/)
+    * Res2Net (https://github.com/gasvn/Res2Net, https://arxiv.org/abs/1904.01169)
+* DLA
+    * Original (https://github.com/ucbdrive/dla, https://arxiv.org/abs/1707.06484)
+    * Res2Net (https://github.com/gasvn/Res2Net, https://arxiv.org/abs/1904.01169)
 * DenseNet (from [torchvision](https://github.com/pytorch/vision/tree/master/torchvision/models))
     * DenseNet-121, DenseNet-169, DenseNet-201, DenseNet-161
 * Squeeze-and-Excitation ResNet/ResNeXt (from [Cadene](https://github.com/Cadene/pretrained-models.pytorch) with some pretrained weight additions by myself)
diff --git a/timm/models/res2net.py b/timm/models/res2net.py
index c2fd3f3b..30dffc1a 100644
--- a/timm/models/res2net.py
+++ b/timm/models/res2net.py
@@ -119,17 +119,6 @@ class Bottle2neck(nn.Module):
         return out
 
 
-
-@register_model
-def res2net50(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
-    """Constructs a Res2Net-50 model.
-    Res2Net-50 refers to the Res2Net-50_26w_4s.
-    Args:
-        pretrained (bool): If True, returns a model pre-trained on ImageNet
-    """
-    return res2net50_26w_4s(pretrained, num_classes, in_chans, **kwargs)
-
-
 @register_model
 def res2net50_26w_4s(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a Res2Net-50_26w_4s model.