1adrianb / 1adrianb/face-alignment

Other models available other than 4-stacked?

未关闭
#4 11 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看
enhancement
主要语言
Python
星标
7.5k
派生
1.4k
PR 合并指标
30 天内没有已合并 PR

描述

Hello Adrian,

Thanks for sharing your code in pytorch. I noticed that you have probably tested several models with less stacked FAN [here](https://github.com/1adrianb/face-alignment/blob/478c38823785db76ca85c059cd455a23a586b663/face_alignment/api.py#L26).

However, only 4-stacked pretrained model is available to download from your website. I would like to know that if it is possible to share smaller models even though the performance might be a little bit worse.

Thank you very much in advance.

贡献指南

这个仓库没有索引到贡献指南

调研方向

The issue references the model loading logic in face_alignment/api.py line 26. Examine the available model configurations and the training pipeline to understand how to produce and share smaller models. Check if there are existing scripts for training different stack counts and what changes are needed to host and serve these models.

由索引模型根据 Issue 内容生成。

评估

技术栈
python, pytorch
领域
ai, machine-learning
Issue 类型
功能
难度
4/5
预计耗时
3-5 天
活跃度
停滞
描述清晰度
描述清楚
新手友好度
35/100

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。