mirrors/pytorch-image-models
1
0
Fork 0
mirror of https://github.com/huggingface/pytorch-image-models.git synced 2025-06-03 15:01:08 +08:00
Code Issues Projects Releases Wiki Activity

Add Res2Net and DLA to README

Browse Source
This commit is contained in:
Ross Wightman 2019-09-04 17:38:59 -07:00
parent adbf770f16
commit 2680ad14bb
2 changed files with 4 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -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) * 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) * '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/) * 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 (from [torchvision](https://github.com/pytorch/vision/tree/master/torchvision/models))
* DenseNet-121, DenseNet-169, DenseNet-201, DenseNet-161 * 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) * Squeeze-and-Excitation ResNet/ResNeXt (from [Cadene](https://github.com/Cadene/pretrained-models.pytorch) with some pretrained weight additions by myself)

11
timm/models/res2net.py
View File

@ -119,17 +119,6 @@ class Bottle2neck(nn.Module):
return out 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 @register_model
def res2net50_26w_4s(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def res2net50_26w_4s(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a Res2Net-50_26w_4s model. """Constructs a Res2Net-50_26w_4s model.