MegEngine / MegEngine/Models

复现 EfficientNet

Open
#41 0 comments 0 reactions 0 assignees View on GitHub
help-wanted
Dominant language
Python
Stars
306
Forks
96
PR merge metrics
No merged PRs in 30d

Description

## 任务描述
- 复现 EfficientNet ,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

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by inspecting the existing model layout under official/vision/classification/models and the repository's training entry points. Use ImageNet as the dataset and verify that the training script completes and reaches the paper's reported accuracy. Done means the implementation, trained weight file, and submission to MegEngine/Hub are provided.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.