未验证 提交 7f128c3a 编写于 作者: L littletomatodonkey 提交者: GitHub

Merge pull request #247 from littletomatodonkey/fix_hrnet_resize

fix typo
......@@ -2,7 +2,7 @@
The ResNeSt series was proposed in 2020. The original resnet network structure has been improved by introducing K groups and adding an attention module similar to SEBlock in different groups, the accuracy is greater than that of the basic model ResNet, but the parameter amount and flops are almost the same as the basic ResNet.
RegNet was proposed in 2020 by FAIR to deepen the concept of design space. Based on AnyNetX, the model performance is gradually improved by shared bottleneck ratio, shared group width, adjusting network depth or width and other strategies. What's more, the design space structure is simplified, whose interpretability is also be improved. The quality of design space is improved while its diversity is maintained. Under similar conditions, the performance of the designed RegNet model performs better than EfficientNet and 5 times faster than EfficientNet.
RegNet was proposed in 2020 by Facebook to deepen the concept of design space. Based on AnyNetX, the model performance is gradually improved by shared bottleneck ratio, shared group width, adjusting network depth or width and other strategies. What's more, the design space structure is simplified, whose interpretability is also be improved. The quality of design space is improved while its diversity is maintained. Under similar conditions, the performance of the designed RegNet model performs better than EfficientNet and 5 times faster than EfficientNet.
## Accuracy, FLOPs and Parameters
......
......@@ -4,7 +4,7 @@
ResNeSt系列模型是在2020年提出的,在原有的resnet网络结构上做了改进,通过引入K个Group和在不同Group中加入类似于SEBlock的attention模块,使得精度相比于基础模型ResNet有了大幅度的提高,且参数量和flops与基础的ResNet基本保持一致。
RegNet是由FAIR于2020年提出,旨在深化设计空间理念的概念,在AnyNetX的基础上逐步改进,通过加入共享瓶颈ratio、共享组宽度、调整网络深度与宽度等策略,最终实现简化设计空间结构、提高设计空间的可解释性、改善设计空间的质量,并保持设计空间的模型多样性的目的。最终设计出的模型在类似的条件下,性能还要由于EfficientNet,并且在GPU上的速度提高了5倍。
RegNet是由facebook于2020年提出,旨在深化设计空间理念的概念,在AnyNetX的基础上逐步改进,通过加入共享瓶颈ratio、共享组宽度、调整网络深度与宽度等策略,最终实现简化设计空间结构、提高设计空间的可解释性、改善设计空间的质量,并保持设计空间的模型多样性的目的。最终设计出的模型在类似的条件下,性能还要优于EfficientNet,并且在GPU上的速度提高了5倍。
## 精度、FLOPS和参数量
......
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