Yunshui Li
Yunshui Li
Have you solved this problem? Thank you!
This is related to the implementation of ConvKB in KGAT, the problem is parameter dependent, sometimes it happens and sometimes it doesn't
I meet the same problem, have you fixed it? Thank you~
You requested GPUs: [0, 1, 2, 3, 4, 5, 6, 7] But your machine only has: [0] You should set the num_gpus hyperparameter in your script.
export NODE_RANK=0
You should learn to debug yourself！ Bro！
transformers的版本不对 使用 pip install transformers==2.11.0
Hello, why do you think the evaluation script evaluates the results of the validation set? I'm a little confused. Can you provide more details~
Oh, I see. Our project is developed based on ViLT, so we used the same tricks [[vilt-datamodule]](https://github.com/dandelin/ViLT/blob/762fd3975c180db6fc88f577cf39549983fa373a/vilt/datamodules/datamodule_base.py#L115) [[vilt-coco-dataset]](https://github.com/dandelin/ViLT/blob/762fd3975c180db6fc88f577cf39549983fa373a/vilt/datasets/coco_caption_karpathy_dataset.py#L12)as they do . If you replace photochat_context_dev with photochat_context_test in the class...
Additionally, you might want to try using a longer context when constructing the data. (https://github.com/AlibabaResearch/DAMO-ConvAI/blob/adcb4950b123eb70266201cb5c0e10894658ec97/pace/pace/utils/write_photochat.py#L46)