zml110120

Results 10 issues of zml110120

Dear author, I have two questions about your latest CVPR2022 paper (Comprehending and Ordering Semantics for Image Captioning). ![image](https://user-images.githubusercontent.com/29172684/178029193-9ff4f4d9-6cd5-4502-be3c-19c1469b4e65.png) 1. What do you means about "slot" in the figure 2?...

Dear author, It is a fantastic work! But there are some problems when i use it. I need to generate captions with punctuations, just like 【There are a, b and...

Dear author @zhangxuying1004 , It is a wonderful work. If my own dataset have not Object Detection Annotation, how can i use your model?

how can i custom my datasets to train PureT model?

Dear author, How can i get origin images tensor (just like the first image) ? Not like `att_feats = kwargs[cfg.PARAM.ATT_FEATS]` tensor (just like the second image). First image ![image](https://user-images.githubusercontent.com/29172684/210171513-ab8ce608-7e2b-410d-bc0f-fc902bc75841.png) Second...

Dear author, I have a question. What is the difference between "-1" in "TARGET_SENT" and "0" in "INPUT_SENT"? Just like the first image and second image? "-1" means padding and...

@232525 Dear author, I use custom datasets. I used preprocess program, and create some files, like fisrt picture. I can get result, but there are some mistakes in "Loading and...

您好,我想咨询您一些关于在MuKEA中使用自定义数据集的问题: 我们的数据集不是通用领域(偏向于医学),格式类似VQA-RAD,导致您提供的pickle、tsv文件不能使用。我需要怎么做才能在我的数据集上使用?

请问,如何使用inference.py或者别的python文件 完成验证或者测试(不训练,直接跑测试集或者验证集)?

hello,deer editor,i want consultation some questions. when i execute python3 scripts/voc_eval.py . i get this error FileNotFoundError: [Errno 2] No such file or directory: 'results/20200423-VOC-base_novel0_neg1/ene000130/aeroplane.txt'。How can i resolve it?