Open 1301358882 opened 2 weeks ago
The embedding method we adopt is random or glove, so this file is not used
The embedding method we adopt is random or glove, so this file is not used
I run bash script/train.sh directly and the error is as follows
Is it because the COCO data set was not downloaded? Where should the COCO data set be stored? See the coco_json_path in coco_data.py that processes the COCO data set. How was this dataset_coco.json file obtained?
Thank you very much!
You can print config_name. You probably didn't download the bert-base-uncased pretrained model structure
Hello, could you please tell me where I can find some of the yaml files mentioned in the code?