2s-AGCN icon indicating copy to clipboard operation
2s-AGCN copied to clipboard

ValueError: invalid literal for int() with base 10: './pre_train/ki_agcn'

Open dongle329 opened this issue 4 years ago • 5 comments

hello when i run python main.py --config ./config/kinetics-skeleton/test_joint.yaml have this problem Traceback (most recent call last): File "main.py", line 577, in processor = Processor(arg) File "main.py", line 213, in init self.load_model() File "main.py", line 249, in load_model self.global_step = int(arg.weights[:-3].split('-')[-1]) ValueError: invalid literal for int() with base 10: './pre_train/ki_agcn

thank you

dongle329 avatar Jul 05 '20 22:07 dongle329

you can set line 249 as self.global_step = 0 since initial command is to load the epoch number of the model when it has one.

erinchen824 avatar Oct 23 '20 09:10 erinchen824

同样的问题,请问如何解决? 仅仅是将self.global_step = 0 吗? 同时模型训练完毕后,并无./pre_train/pd_agcn.pt 该路径以及文件。

YuQi9797 avatar Jul 20 '21 06:07 YuQi9797

同样的问题,请问如何解决? 仅仅是将self.global_step = 0 吗? 同时模型训练完毕后,并无./pre_train/pd_agcn.pt 该路径以及文件。

去test的yaml文件里面将对应的预训练模型位置改成你训练得到的pt文件就可以了,他这个和mmskeleton的测试流程差不多。

doMoreCode avatar Aug 13 '21 09:08 doMoreCode

hello when i run python main.py --config ./config/kinetics-skeleton/test_joint.yaml have this problem Traceback (most recent call last): File "main.py", line 577, in processor = Processor(arg) File "main.py", line 213, in init self.load_model() File "main.py", line 249, in load_model self.global_step = int(arg.weights[:-3].split('-')[-1]) ValueError: invalid literal for int() with base 10: './pre_train/ki_agcn

thank you

maybe check your pt path in test yaml, i got the result after this.

doMoreCode avatar Aug 13 '21 09:08 doMoreCode

好的,俺去试试! 感谢!

------------------ 原始邮件 ------------------ 发件人: "lshiwjx/2s-AGCN" @.>; 发送时间: 2021年8月13日(星期五) 下午5:36 @.>; @.@.>; 主题: Re: [lshiwjx/2s-AGCN] ValueError: invalid literal for int() with base 10: './pre_train/ki_agcn' (#57)

hello when i run python main.py --config ./config/kinetics-skeleton/test_joint.yaml have this problem Traceback (most recent call last): File "main.py", line 577, in processor = Processor(arg) File "main.py", line 213, in init self.load_model() File "main.py", line 249, in load_model self.global_step = int(arg.weights[:-3].split('-')[-1]) ValueError: invalid literal for int() with base 10: './pre_train/ki_agcn

thank you

maybe check your pt path in test yaml, i got the result after this.

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.

YuQi9797 avatar Aug 13 '21 10:08 YuQi9797