‘best_model.path’ about jmodt HOT 5 OPEN

Hi, I also have the same problem, did you solve it?

from jmodt.

hey bro. do u meet the problem when training the model “that UnboundLocalError: local variable 'val_loss_epoch' referenced before assignment #2”

Thanks a lot.

from jmodt.

@zzm-hl @ynlx
Excuse me，I meet same problems.
No.1 ”UnboundLocalError: local variable 'val_loss_epoch' referenced before assignment“；
For this problem I change some code then the problem fixed，but it comes new problem that same with this.

No.2 “best_model.path” is not update.

对不起，我也遇到同样的问题。
第1条问 “UnboundLocalError:赋值前引用的局部变量‘val_loss_epoch’”；对于这个问题，我更改了一些代码，然后问题得到了解决，但随之而来的是新问题。
第2条 “best_model.path”未更新。

from jmodt.

Thank you very much for your work. I noticed that the best checkpoint doesn't seem to have been updated while I was training, is this normal?

I meet the same problem，I found that 'rcnn_link_pos': 0.0, 'rcnn_link_neg': 0.0, 'rcnn_start_pos': 0.0, 'rcnn_start_neg': 0.0, 'rcnn_end_pos': 0.0, 'rcnn_end_neg': 0.0 when I run the train.py. I think the best_model.pth not update because of these parameters are always zero.

from jmodt.

@zzm-hl @ynlx Excuse me，I meet same problems. No.1 ”UnboundLocalError: local variable 'val_loss_epoch' referenced before assignment“； For this problem I change some code then the problem fixed，but it comes new problem that same with this.

No.2 “best_model.path” is not update.

对不起，我也遇到同样的问题。 第1条问 “UnboundLocalError:赋值前引用的局部变量‘val_loss_epoch’”；对于这个问题，我更改了一些代码，然后问题得到了解决，但随之而来的是新问题。 第2条 “best_model.path”未更新。

Hello dear @zzm-hl, How did you change your code for error 1? ”UnboundLocalError: local variable 'val_loss_epoch' referenced before assignment“ “UnboundLocalError:赋值前引用的局部变量‘val_loss_epoch’”；对于这个问题，我更改了一些代码"

from jmodt.