Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
huicui 20c6023900 | 2 years ago | |
---|---|---|
.. | ||
lr_scheduler | 2 years ago | |
CrossEntropySmooth.py | 2 years ago | |
__init__.py | 2 years ago | |
config.py | 2 years ago | |
dataset.py | 2 years ago | |
spnasnet.py | 2 years ago | |
utils.py | 2 years ago |
Single_Path_NAS通过一个7x7的卷积来替换3x3、5x5和7x7的三种卷积(外边一圈mask清零可以变成3x3或5x5),这个大的卷积成为superkernel,于是整个网络只有一种卷积,看起来是一个直筒结构。搜索空间是基于block的直筒结构,跟ProxylessNAS和FBNet一样,都采用Inverted Bottleneck 作为cell, 层数跟MobileNetV2一样都是22层,每层只有两个参数 expansion rate, kernel size需要搜索,其他都已固定,比如22层中每层的filter number已固定死,跟FBNet一样,跟MobileNetV2比略有变化。论文中的kernel size和FBNet、 ProxylessNAS一样只有3x3和5x5两种,没有用上7x7。论文中的expansion ratio也只有3和6两种选择。kernel size 和 expansion ratio都只有2种选择,论文选择用Lightnn这篇论文中的手法,把离散选择用连续的光滑函数来表示,阈值用group Lasso term。论文用了跟ProxylessNAS一样的手法来表达skip connection, 用一个zero layer表示。
Python C++ Shell Text
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》