评价指标报错

[zhoulian-sudo]

您好，周梓康博士，感谢您杰出的代码贡献，想问下您评价指标处一直报这种错误是什么原因？？ 报错处：class ADE(Metric):

def __init__(self,
             compute_on_step: bool = True,
             dist_sync_on_step: bool = False,
             process_group: Optional[Any] = None,
             dist_sync_fn: Callable = None) -> None:
    super(ADE, self).__init__(compute_on_step=compute_on_step, dist_sync_on_step=dist_sync_on_step,
                              process_group=process_group, dist_sync_fn=dist_sync_fn)
    self.add_state('sum', default=torch.tensor(0.0), dist_reduce_fx='sum')
    self.add_state('count', default=torch.tensor(0), dist_reduce_fx='sum')

错误： Global seed set to 2022 /home/amax/anaconda3/envs/haha/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/accelerator_connector.py:466: LightningDeprecationWarning: Setting Trainer(gpus=1) is deprecated in v1.7 and will be removed in v2.0. Please use Trainer(accelerator='gpu', devices=1) instead. rank_zero_deprecation( GPU available: True (cuda), used: True TPU available: False, using: 0 TPU cores IPU available: False, using: 0 IPUs HPU available: False, using: 0 HPUs Traceback (most recent call last): File "/data/project/HiVT-main/train.py", line 44, in model = HiVT(**vars(args)) File "/data/project/HiVT-main/models/hivt.py", line 86, in init self.minADE = ADE() File "/data/project/HiVT-main/metrics/ade.py", line 27, in init super(ADE, self).init(compute_on_step=compute_on_step, dist_sync_on_step=dist_sync_onstep, File "/home/amax/anaconda3/envs/haha/lib/python3.9/site-packages/torchmetrics/metric.py", line 145, in init raise ValueError(f"Unexpected keyword arguments: {', '.join(kwargs)}") ValueError: Unexpected keyword arguments: compute_on_step

[LL-C8]

@zhoulian-sudo 同样遇到了这个问题，请问解决了吗？

[zhoulian-sudo]

不好意思，我这边也没有解决 

冰糖?葫芦 @.***

 

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2023年8月6日(星期天) 下午4:22 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [ZikangZhou/HiVT] 评价指标报错 (Issue #41)

@zhoulian-sudo 同样遇到了这个问题，请问解决了吗？

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.***>

[Lewis-Lu]

Hi there,

Could you please check the version of torchmetrics using pip list | grep torchmetrics.

As far as I know, Metrics has deprecate the compute_on_step parameter from certain version.

Thanks Lewis

[xuyangwenhui]

I solved the same problem by using commod " pip install torchmetrics==0.8.2 ", maybe you could reference the issue " https://github.com/Lightning-AI/torchmetrics/issues/789 "

[zhaozhen2333]

I solved the same problem by using commod " pip install torchmetrics==0.8.2 ", maybe you could reference the issue " Lightning-AI/torchmetrics#789 "

Thank you very much

[alien-HL]

把3个评价指标的文件中，super初始化里的compute_on_step关键字去掉就可以