search

fangchangma / self-supervised-depth-completion

ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera"
MIT License
630 stars 134 forks source link

About extracting trained model #39

Open JuewenPeng opened 4 years ago

JuewenPeng commented 4 years ago

When I downloaded the trained model, I could not extract the 'tar' file. I was wondering if there is something wrong with your 'tar' file.

fangchangma commented 4 years ago

The .tar files are not compressed - they are simply pytorch-saved dictionaries. In other words, load them directly from pytorch without any decompression.

JuewenPeng commented 4 years ago

Thank you for your reply. I truly appreciate your help in resolving my problem.

发自我的iPhone

------------------ Original ------------------ From: Fangchang Ma <notifications@github.com> Date: Sun,Mar 22,2020 5:06 PM To: fangchangma/self-supervised-depth-completion <self-supervised-depth-completion@noreply.github.com> Cc: Suraimu <2661843290@qq.com>, Author <author@noreply.github.com> Subject: Re: [fangchangma/self-supervised-depth-completion] About extracting trained model (#39)

The .tar files are not compressed - they are simply pytorch-saved dictionaries. In other words, load them directly from pytorch without any decompression.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.