SwinTextSpotter
SwinTextSpotter copied to clipboard
mxin262
Pytorch re-implementation of Paper: SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition (CVPR 2022)
File "demo/demo.py", line 87, in cfg = setup_cfg(args) File "demo/demo.py", line 33, in setup_cfg cfg.merge_from_file(args.config_file) File "/home/111/.local/lib/python3.8/site-packages/detectron2/config/config.py", line 69, in merge_from_file self.merge_from_other_cfg(loaded_cfg) File "/home/111/.local/lib/python3.8/site-packages/fvcore/common/config.py", line 132, in merge_from_other_cfg return super().merge_from_other_cfg(cfg_other)...
显示找不到'move_device_like'文件,我在您的项目里面也没有找到该文件,请问您那有这个文件吗?报错如下: Traceback (most recent call last): File "E:\Pytorch_code\SwinTextSpotter\demo\demo.py", line 14, in from predictor import VisualizationDemo File "E:\Pytorch_code\SwinTextSpotter\demo\predictor.py", line 10, in from detectron2.engine.defaults import DefaultPredictor File "E:\Pytorch_code\SwinTextSpotter\detectron2\engine\__init__.py", line 12, in from...
RuntimeError: cannot reshape tensor of 0 elements into shape [0, 256, -1] because the unspecified dimension size -1 can be any value and is ambiguous 经常碰到这个问题，虽然后面能继续跑，但是可能会影响效果，请问该怎么样避免。
