Skip to content

复现 Googlenet #40

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
xxr3376 opened this issue Jul 3, 2020 · 4 comments
Open

复现 Googlenet #40

xxr3376 opened this issue Jul 3, 2020 · 4 comments

Comments

@xxr3376
Copy link
Member

xxr3376 commented Jul 3, 2020

任务描述

  • 复现 Googlenet ,训练正常收敛,验收指标符合预期,并将代码提交到 offical/vision/classification/models 下

目标

  • 数据集ImageNet
  • 准确率和论文一致或更高
  • 脚本可以完整完成训练步骤
  • 提供训练后的权重文件
  • 提交至 https://github.com/MegEngine/Hub
@lijiansong
Copy link
Contributor

@xxr3376最近在试用meg-engine推出的大模型训练的dtr功能,发现model zoo里都没有vgg这种经典的模型:-)
感觉类似这种https://www.tensorflow.org/api_docs/python/tf/keras/applications模型官方repo都应该有啊

@xxr3376
Copy link
Member Author

xxr3376 commented Apr 25, 2021

@lijiansong VGG 这些模型实在有些古老,所以在复现的时候就没有首先选这些。欢迎大家给我们的 ModelHub 提交模型呀~

@cheekyshibe
Copy link

@xxr3376 还有个问题,目前的算子列表里没有topk这种算子,所以如果想实现基本的机器学习算法,如kNN、决策树、kmeans等这些算法,暂时做不了?

你指的是 megengine.functional.topk 吗?

@lijiansong
Copy link
Contributor

@MegChai 是的,看了一下列表,还是挺完备的

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

3 participants