search

VIPL-SLP / VAC_CSLR

Visual Alignment Constraint for Continuous Sign Language Recognition. ( ICCV 2021)
https://openaccess.thecvf.com/content/ICCV2021/html/Min_Visual_Alignment_Constraint_for_Continuous_Sign_Language_Recognition_ICCV_2021_paper.html
Apache License 2.0
116 stars 19 forks source link

Data augmention error #35

Closed btt-creator closed 1 year ago

btt-creator commented 1 year ago

Hi,author! I'm doing a data augmentation task，and I get problems every time I run to batch 777(The training set is twice as large as before)。I've seen your previous answer about "Index error:list out of range" but I have detected that the frame path is correct。（by the way batch_size is 4,device is 4） image

ycmin95 commented 1 year ago

Hi @tanbitao, you can try to capture this index error and provide more details about this error.

btt-creator commented 1 year ago

thank you，author！i‘ve solved this question!

btt-creator commented 1 year ago

thank you！i’ve solved this question!Have a good day!

------------------ 原始邮件 ------------------ 发件人: "ycmin95/VAC_CSLR" @.>; 发送时间: 2023年4月23日(星期天) 晚上9:20 @.>; @.**@.>; 主题: Re: [ycmin95/VAC_CSLR] Data augmention error (Issue #35)

Hi @tanbitao, you can try to capture this index error and provide more details about this error.

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

WhiteButterflies commented 1 year ago

The csv file have a broken data.In the vac code,the author had deleted it.when we change the csv file,we should delete anthoner data. 做数据增强时，将csv文件扩充了两倍，但是之前的csv文件里面2390这个数据是坏的，当我们扩充时，需要将对应2390的那条数据也做drop处理。