qin79 comments

Results 3 comments of


                                            qin79

Could you share the class labels of VQA object detection using Faster R-CNN?

if i want to get the class(label) of the bounding box, how can i do? should i rewrite the **bottom-up-attention/tools/generate_tsv.py** to get?

More evaluation methods including CIDEr, METEOR and ROUGE besides BLEU1-4

> @ ruizhao1997您好，我尝试使用指标CIDEr，METEOR和ROUGE进行评估。但是，METEOR出了点问题。 > > 回溯（最后最近一次调用）： > 文件“eval.py”，线200，在 > score_dict =评估（beam_size） > 文件“eval.py”，线190，在评估 > score_i，scores_i = scorer.compute_score（REF，海波） > 文件“ /Users/Ryan/a-PyTorch-Tutorial-to-Image-captioning-master/evalfunc/meteor/meteor.py”，第41行，位于compute_score > stat = self._stat（res [i] [0]，gts [ i]） > 在“...

how can we use the model we trained to transfer the sentence we specified?

and if anybody has the code for Human Evaluation?