未验证 提交 5117de4a 编写于 作者: L Luke Melas-Kyriazi 提交者: GitHub

Update README.md

上级 3d400a58
......@@ -10,6 +10,17 @@ model = EfficientNet.from_pretrained('efficientnet-b0')
### Updates
#### Update (April 2, 2021)
The [EfficientNet-v2 paper]() has been released! I am working on implementing it as you read this :)
About EfficientNet-v2:
> EfficientNetV2 is a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models. To develop this family of models, we use a combination of training-aware neural architecture search and scaling, to jointly optimize training speed and parameter efficiency. The models were searched from the search space enriched with new ops such as Fused-MBConv.
Here is a comparison:
> <img src="https://github.com/lukemelas/EfficientNet-v2-PyTorch/releases/download/v0.0.1/image.png" width="100%" />
#### Update (Aug 25, 2020)
This update adds:
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册