yuqinie98 / PatchTST

An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730
Apache License 2.0
1.37k stars 248 forks source link

关于model参数的问题 #69

Open 1348598339 opened 11 months ago

1348598339 commented 11 months ago

请问为什么model参数里面只有informer、autoformer等几个模型啊,没有见到pathctst

yuqinie98 commented 11 months ago

Hi, the model is here: https://github.com/yuqinie98/PatchTST/blob/main/PatchTST_supervised/models/PatchTST.py

ZZD-guardian commented 7 months ago

so this means when i run the experiments, i need to change the default value for "args.model" into 'Patch TST' and then all fixed out? and that's for the code in exp_main.py import PatchTST already

LHF827 commented 6 months ago

class Exp_Main(Exp_Basic): def init(self, args): super(Exp_Main, self).init(args)

def _build_model(self):
    model_dict = {
        'Autoformer': Autoformer,
        'Transformer': Transformer,
        'Informer': Informer,
        'DLinear': DLinear,
        'NLinear': NLinear,
        'Linear': Linear,
        'PatchTST': PatchTST,
    }
    model = model_dict[self.args.model].Model(self.args).float()

最后一行什么意思 .model不太懂 PatchTST模型 在文件里面写的是model类

codeNiuMa commented 3 months ago
    parser.add_argument('--model', type=str, default='PatchTST',
                        help='model name, options: [Autoformer, Informer, Transformer]')

这里写的不全,model可以是任何一个'Autoformer''Transformer','Informer','DLinear', 'NLinear' 'Linear' 'PatchTST'