Splendon

could you use English?

你解决转化的问题没有啦

我用这行命令 python pytorch_transformers/convert_xlnet_checkpoint_to_pytorch.py --tf_checkpoint_path XLNet_zh_Large_L-24_H-1024_A-16/xlnet_model.ckpt --xlnet_config_file XLNet_zh_Large_L-24_H-1024_A-16/xlnet_config.json --pytorch_dump_folder_path XLNet_zh_Large_L-24_H-1024_A-16 而且，把xlnet_model.ckpt改名为xlnet_model.ckpt.data-00000-of-00001，就可以顺利转换了

我用这行命令 python pytorch_transformers/convert_xlnet_checkpoint_to_pytorch.py --tf_checkpoint_path XLNet_zh_Large_L-24_H-1024_A-16/xlnet_model.ckpt --xlnet_config_file XLNet_zh_Large_L-24_H-1024_A-16/xlnet_config.json --pytorch_dump_folder_path XLNet_zh_Large_L-24_H-1024_A-16 而且，把xlnet_model.ckpt改名为xlnet_model.ckpt.data-00000-of-00001，就可以顺利转换了

You can train yolor with img-size of 640 on yourself on coco2017. If train with 8 cards A100，it needs about 4 days to reproduce the result of yolor. Or, you...

there is not yolor-p7, are you meaning the scaled-yolov4-p7?

hi @qutyyds, you can refer to this github project, https://github.com/DataXujing/YOLOR-

You can copy the curl to browser to get pretrained models.

Is there any progress?