小白在使用模型训练时出现，KeyError: 'LinearWarmup_LR'
收藏
在自己的电脑上下载了ch_PP-OCRv2_rec_slim训练模型，把训练和测试图片和标注路径修改了，然后使用python tools/train.py -c configs/rec/ch_PP-OCRv2_rec.yml -o Global.checkpoints=./output/rec_mobile_pp-OCRv2/best_accuracy命令，接着跳出这个问题，请问是怎么回事呢？
0
收藏
请登录后评论
以下是问题上面的提示代码
Traceback (most recent call last):
File "E:\softwares\anaconda\PaddleOCR-release-2.4\PaddleOCR-release-2.4\tools\train.py", line 148, in
main(config, device, logger, vdl_writer)
File "E:\softwares\anaconda\PaddleOCR-release-2.4\PaddleOCR-release-2.4\tools\train.py", line 100, in main
pre_best_model_dict = load_model(config, model, optimizer)
File "E:\softwares\anaconda\PaddleOCR-release-2.4\PaddleOCR-release-2.4\ppocr\utils\save_load.py", line 83, in load_model
optimizer.set_state_dict(optim_dict)
File "E:\softwares\anaconda\lib\site-packages\decorator.py", line 232, in fun
return caller(func, *(extras + args), **kw)
File "E:\softwares\anaconda\lib\site-packages\paddle\fluid\wrapped_decorator.py", line 25, in __impl__
return wrapped_func(*args, **kwargs)
File "E:\softwares\anaconda\lib\site-packages\paddle\fluid\framework.py", line 229, in __impl__
return func(*args, **kwargs)
File "E:\softwares\anaconda\lib\site-packages\paddle\optimizer\optimizer.py", line 287, in set_state_dict
self._learning_rate.set_state_dict(state_dict["LR_Scheduler"])
File "E:\softwares\anaconda\lib\site-packages\paddle\optimizer\lr.py", line 794, in set_state_dict
self.learning_rate.set_state_dict(state_dict["LinearWarmup_LR"])