Issues
- 0
Confusion about the IRR module
#38 opened by shallowzz - 0
CUHK-PEDES
#34 opened by LYY123444 - 0
想问一下想得到主观结果是运行哪个文件呢
#37 opened by xiaoxiao12580 - 0
The nan error
#36 opened by tengxiao14 - 0
请问谁有ICFG-PEDES数据集,救救孩子,发邮件给作者三天了也没有回复
#35 opened by Gpn-star - 1
How to specify a particular GPU to train?
#30 opened by ppsychoo - 2
Multi gpu training problem
#23 opened by Qusijia - 0
Maybe an error in the original paper?
#33 opened by ThomasjonLi - 1
- 0
Maybe an error
#32 opened by ThomasjonLi - 2
a small bug about RSTPReid dataset
#31 opened by shujielan - 1
- 0
PROBLEMS REGARDING DIFFRENT SPIT OF DATASET
#25 opened by hungphongtrn - 1
How to Solve multi-GPU Training Problems?
#22 opened by Rewinner991130 - 1
There is a mistake that the mlm module that the mask token's output and the whole token
#29 opened by jssyzsfzy - 2
文本全局特征如何获得?
#28 opened by shams2023 - 0
KeyError: 'mlm_ids'
#27 opened by yangmengmeng123 - 0
The id loss in the table is not a separate loss, but is trained jointly with the itc loss in the baseline.
#26 opened by shams2023 - 0
Is it unfair to use a pre-trained CLIP model compared to some other methods in Table 1?
#24 opened by maoSuxi - 4
A small multi GPU training bug
#5 opened by Aotle - 1
Confusion about the setting of validation dataset
#20 opened by YwSama - 1
About using RN50 as image encoder
#18 opened by sunmenmian - 3
- 11
- 2
- 0
table4. cuhk-pedes rank1 maybe typos~
#15 opened by panqihe-zjut - 3
- 1
关于id_loss在训练过程中不收敛的问题
#9 opened by Zplusdragon - 1
- 2
Missing resize_text_pos_embed in clip_model.py
#10 opened by AwePhD - 2
- 2
cant use best.pth
#7 opened by Justhuayu - 0
about the CUHK-PEDES dataset
#6 opened by Justhuayu - 1
Unexpected keyword argument 'batch_first'
#4 opened by LKRCharon - 2
请问哪里可以看到论文?
#3 opened by LinDixuan - 1
A small bug
#2 opened by YwSama - 4
About ICFG-PEDES dataset
#1 opened by ljwwwiop