KeyError: 'LinearWarmup_LR' error while custom training with transfer learning from default best_accuracy models

[anidiatm41]

[2022/09/13 15:24:00] ppocr INFO: valid dataloader has 31 iters Traceback (most recent call last): File "tools/train.py", line 202, in main(config, device, logger, vdl_writer) File "tools/train.py", line 169, in main pre_best_model_dict = load_model(config, model, optimizer, File "C:\Users\1619872\Desktop\paddleocr_2\ppocr\utils\save_load.py", line 124, in load_model optimizer.set_state_dict(optim_dict) File "C:\Users\1619872\AppData\Local\conda\conda\envs\torch\lib\site-packages\decorator.py", line 232, in fun return caller(func, *(extras + args), **kw) File "C:\Users\1619872\AppData\Local\conda\conda\envs\torch\lib\site-packages\paddle\fluid\wrapped_decorator.py", line 25, in impl return wrapped_func(*args, **kwargs) File "C:\Users\1619872\AppData\Local\conda\conda\envs\torch\lib\site-packages\paddle\fluid\framework.py", line 434, in impl return func(*args, **kwargs) File "C:\Users\1619872\AppData\Local\conda\conda\envs\torch\lib\site-packages\paddle\optimizer\optimizer.py", line 305, in set_state_dict self._learning_rate.set_state_dict(state_dict["LR_Scheduler"]) File "C:\Users\1619872\AppData\Local\conda\conda\envs\torch\lib\site-packages\paddle\optimizer\lr.py", line 799, in set_state_dict self.learning_rate.set_state_dict(state_dict["LinearWarmup_LR"]) KeyError: 'LinearWarmup_LR'

[anidiatm41]

any idea how to fix the issue?

[anidiatm41]

I am using below parameters in yml file:

pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained checkpoints: C:/Users/1619872/Desktop/ch_en2/ch_ppocr_mobile_v2.0_det_train/best_accuracy

[anidiatm41]

@Evezerest

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.