Can you tell me how do you get the ext_audio from AIST++? I can't find this directory

<a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/us

The way to get ext_audio,about guhuangai/gcdg

GuHuangAI commented on September 2, 2024

Hello, I'm sorry that I have forgot the detail of downloading the dataset.
You can try some links in https://google.github.io/aistplusplus_dataset/download.html.

from gcdg.

mucunzhuzhu commented on September 2, 2024

I am so happy that you reply to me so quickly.  I have tried many times, but I didn't find the correct directory. If it's convenient for you, could you send me the "ext_audio" directory directly? ***@***.*** ***@***.***  

…

------------------ 原始邮件 ------------------ 发件人: "GuHuangAI/GCDG" ***@***.***>; 发送时间: 2023年11月25日(星期六) 下午4:27 ***@***.***>; ***@***.******@***.******@***.***>; 主题: Re: [GuHuangAI/GCDG] The way to get ext_audio (Issue #1) Hello, I'm sorry that I have forgot the detail of downloading the dataset. You can try some links in https://google.github.io/aistplusplus_dataset/download.html. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***>

from gcdg.

GuHuangAI commented on September 2, 2024

I check the code and paths and find that you should download the raw data firstly, and refer to https://github.com/GuHuangAI/GCDG/blob/master/utils/extract_audio.py to obtain the ext_audio directory.
Hope can help u.

from gcdg.

mucunzhuzhu commented on September 2, 2024

I see. In your README.md, you wrote this: So, in the beginning, I thought "ext_audio" is the raw data.   Now, what's the real raw data? Could you send me the raw data directly? ***@***.*** ***@***.***  

…

------------------ 原始邮件 ------------------ 发件人: "GuHuangAI/GCDG" ***@***.***>; 发送时间: 2023年11月25日(星期六) 下午4:59 ***@***.***>; ***@***.******@***.******@***.***>; 主题: Re: [GuHuangAI/GCDG] The way to get ext_audio (Issue #1) I check the code and paths and find that you should download the raw data firstly, and refer to https://github.com/GuHuangAI/GCDG/blob/master/utils/extract_audio.py to obtain the ext_audio directory. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***>

from gcdg.

GuHuangAI commented on September 2, 2024

I see. In your README.md, you wrote this: So, in the beginning, I thought "ext_audio" is the raw data. Now, what's the real raw data? Could you send me the raw data directly? @.*** @.***
…
------------------ 原始邮件 ------------------ 发件人: "GuHuangAI/GCDG" @.>; 发送时间: 2023年11月25日(星期六) 下午4:59 @.>; @.@.@.>; 主题: Re: [GuHuangAI/GCDG] The way to get ext_audio (Issue #1) I check the code and paths and find that you should download the raw data firstly, and refer to https://github.com/GuHuangAI/GCDG/blob/master/utils/extract_audio.py to obtain the ext_audio directory. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.>

The raw data is the video data with suffix .mp4. You can download the data from here

from gcdg.

mucunzhuzhu commented on September 2, 2024

I have successfully run your code! Thank you so much!  But I still have a question which bothers me for days. I wonder why you execute smpl.forward process for the generated pred_poses and pred_trans.  For example, in your core/test2.py, you wrote: I find many theses have done this. But there are also some theses just perform forward kinematics for the generated poses and trans. Do you know the difference between smpl.forward and forward kinematics here?  What's more, I don't understand why we have to evaluate keypoint3d_pre and keypoints3d_tgt instead of directly evaluate the pred_poses.  I am looking forward to your reply.   ***@***.*** ***@***.***  

…

------------------ 原始邮件 ------------------ 发件人: ***@***.***>; 发送时间: 2023年11月25日(星期六) 下午5:58 收件人: ***@***.***>; 抄送: ***@***.******@***.***>; ***@***.***>; 主题: Re: [GuHuangAI/GCDG] The way to get ext_audio (Issue #1) I see. In your README.md, you wrote this: So, in the beginning, I thought "ext_audio" is the raw data.   Now, what's the real raw data? Could you send me the raw data directly? @.*** @.***   … ------------------ 原始邮件 ------------------ 发件人: "GuHuangAI/GCDG" @.>; 发送时间: 2023年11月25日(星期六) 下午4:59 @.>; @.@.@.>; 主题: Re: [GuHuangAI/GCDG] The way to get ext_audio (Issue #1) I check the code and paths and find that you should download the raw data firstly, and refer to https://github.com/GuHuangAI/GCDG/blob/master/utils/extract_audio.py to obtain the ext_audio directory. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> The raw data is the video data with suffix .mp4. You can download the data from [here]([https://google.github.io/aistplusplus_dataset/download.html]. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***>

from gcdg.

GuHuangAI commented on September 2, 2024

@mucunzhuzhu Congratulations for your job.
However, there are some wrong symbols in your reply, I can hardly understand it.

from gcdg.

The way to get ext_audio about gcdg HOT 7 OPEN

Comments (7)

Related Issues (1)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent