AttributeError: 'NoneType' object has no attribute 'lower'

[lw0210]

Dear, I download your dataset (taskeconomy, diversedepth, hwrsi and holopix50k) by running sh Download_ data. sh, and run your recently updated code. I can run sh train_ demo. sh, but cannot run sh train.sh. I modify the parameter dataset_ list in train.sh (only HWRSI is left，others are not allowed), you can run for a while and then report an error:

AttributeError: 'NoneType' object has no attribute 'lower'

I think it is the lack of content in the datasets.Can you check your dataset？Thanks！

[guangkaixu]

Hi, it seems there exists some invalid file paths in the annotation files. I will double-check them and release as soon as possible. Thanks!

[lw0210]

Thanks！Thank you. Maybe my network is unstable ，so can't downloaded it completely.I'm downloading it again and I get a  reply from others saying that "two of them cannot be used during val (hwrsi and holopix50k) because the read data depth and disp are inconsistent".

------------------ 原始邮件 ------------------ 发件人: "Guangkai @.>; 发送时间: 2022年8月11日(星期四) 下午4:52 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [aim-uofa/AdelaiDepth] AttributeError: 'NoneType' object has no attribute 'lower' (Issue #48)

Hi, it seems there exists some invalid file paths in the annotation files. I will double-check them and release as soon as possible. Thanks!

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

[guangkaixu]

@lw0210 This bug happened because the validation datasets should contain depth images rather than disparity images, which have been fixed just now. Please download the latest annotation files of taskonomy in download_data.sh and pull the latest code. Thank you!

[lw0210]

Thank you. I'll try again

------------------ 原始邮件 ------------------ 发件人: "aim-uofa/AdelaiDepth" @.>; 发送时间: 2022年8月16日(星期二) 晚上7:08 @.>; @.@.>; 主题: Re: [aim-uofa/AdelaiDepth] AttributeError: 'NoneType' object has no attribute 'lower' (Issue #48)

@lw0210 This bug happened because the validation datasets should contain depth images rather than disparity images, which have been fixed just now. Please download the latest annotation files of taskonomy in download_data.sh pull the latest code. Thank you!

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.***>