Zhihong Chen

Hi @lucasjinreal, Thanks for your attention. Yes, we are working on the bloom.cpp and llama.cpp versions. Stay tuned! :-) Best, Zhihong

@cl-cqupt Thanks for your attention. The following might be the solutions: * If you are debugging the dataset/dataloader, set num_worker to 0; * If you are debugging the training process,...

Hi all, Thanks for your attention to our paper! I wrote an example code to compute the score [here](https://github.com/zhjohnchan/R2GenCMN/blob/main/compute_ce.py). Best, Zhihong

Hi there, Thanks for your attention. The operation is allowed since the downloaded RoBERTa model is the same one. Best, Zhihong

Hi, I used A100-80G in my experiments. Best, Zhihong

Hi, I request the dataset from the authors. I think you can send an e-mail to the author. Best, Zhihong

Hello Fanjian @Fan-Jian-Zheng, Thanks for your attention! You can use either [chestpert](https://github.com/MIT-LCP/mimic-cxr/tree/master/txt/chexpert) or [chexbert](https://github.com/stanfordmlgroup/CheXbert) to obtain the disease labels of the generated and reference reports and then compute the P,...

Hi all, Thanks for your attention! I wrote an example code to compute the score [here](https://github.com/zhjohnchan/R2GenCMN/blob/main/compute_ce.py). Best, Zhihong

Hi there, Thanks for your attention! You can ignore that. It just tells us it will create the folder and store the results there. Best, Zhihong

Hi, here are some suggestions: (1) you can use 1 GPU for debugging so you can insert traces in your program; (2) then you can find the place it stuck....