王鹤男

I think it's your network configuration error. If you are using AWS or other cloud services, you should change the security group inbound rules like this: ![Screen Shot 2020-01-20 at...

The problem is fixed by: https://github.com/hpcaitech/ColossalAI/pull/2443, but you have to build ColossalAI from source, since the commit is not included in latest 0.2.5.

You should use `tokenizer.save_pretrained('YOUR_PATH')` to save the tokenizer as well as the model.

I used Yolov5 to train the model, but I think Yolov8 is similar

Yes, I didn't train the Fintab Dataset. But maybe you can merge the dataset with PubTables-1M. I also recommend you to set Yolo `size` to at least 800 to get...

1. The weights are here: https://github.com/whn09/table_structure_recognition/tree/main/yolov5/runs 2. When I trained the model, yolov5 is the latest model. You can try Yolov8 or other object detection models as well.

Hi, Thank you for you feedback and questions. And I will explain my method here: - I used all PubTables-1M train data to train the yolov5s model, and use test...

Hi, I trained the models for about 10 hours/model on AWS ml.p3.2xlarge (1 NVIDIA V100 GPU (16GB GPU Memory), 8 CPU, 64GB RAM).

I think PaddleOCR is suitable for English and Chinese, and Amazon Textract or other SaaS services may be better.