RuntimeError:在预测中，分位数()q张量必须与输入张量相同。

Question

• PyTorch-Forecasting版本: 0.10.2
• PyTorch

System: windows

预期行为

无差错

实际行为

错误是

File DistributionLoss.to_quantiles(self，y_pred，分位数，n_samples) 977 (NotImplementedError除外) 978个样本= torch.sort(self.sample(y_pred，n_samples)，-1).values -> 979分位数=torch.quantile(样本，torch.tensor，device=samples.device)，dim=2).permute(1，2，980返回分位数RuntimeError:分位数()q张量必须与输入张量相同的dtype

如何将它们设置为相同的数据类型？这是在内部发生的。我无法控制这件事。我不使用任何GPU。

带有输入数据的.csv文件的链接是https://github.com/JosePeeterson/Demand_forecasting，每4小时从负的二进制分布(9,0.5)中采样数据。中间的时间都是零。我只想看看DeepAR是否能学到这种模式。

再现问题的代码

from pytorch_forecasting.data.examples import generate_ar_data
import matplotlib.pyplot as plt
import pandas as pd
from pytorch_forecasting.data import TimeSeriesDataSet
from pytorch_forecasting.data import NaNLabelEncoder
from pytorch_lightning.callbacks import EarlyStopping, LearningRateMonitor
import pytorch_lightning as pl
from pytorch_forecasting import NegativeBinomialDistributionLoss, DeepAR
import torch
from pytorch_forecasting.data.encoders import TorchNormalizer

data = [pd.read_csv('1_f_nbinom_train.csv')]

data["date"] = pd.Timestamp("2021-08-24") + pd.to_timedelta(data.time_idx, "H")
data['_hour_of_day'] = str(data["date"].dt.hour)
data['_day_of_week'] = str(data["date"].dt.dayofweek)
data['_day_of_month'] = str(data["date"].dt.day)
data['_day_of_year'] = str(data["date"].dt.dayofyear)
data['_week_of_year'] = str(data["date"].dt.weekofyear)
data['_month_of_year'] = str(data["date"].dt.month)
data['_year'] = str(data["date"].dt.year)

max_encoder_length = 60
max_prediction_length = 20
training_cutoff = data["time_idx"].max() - max_prediction_length

training = TimeSeriesDataSet(
    data.iloc[0:-620],
    time_idx="time_idx",
    target="value",
    categorical_encoders={"series": NaNLabelEncoder(add_nan=True).fit(data.series), "_hour_of_day": NaNLabelEncoder(add_nan=True).fit(data._hour_of_day), \
       "_day_of_week": NaNLabelEncoder(add_nan=True).fit(data._day_of_week), "_day_of_month" : NaNLabelEncoder(add_nan=True).fit(data._day_of_month), "_day_of_year" : NaNLabelEncoder(add_nan=True).fit(data._day_of_year), \
        "_week_of_year": NaNLabelEncoder(add_nan=True).fit(data._week_of_year), "_year": NaNLabelEncoder(add_nan=True).fit(data._year)},
    group_ids=["series"],
    min_encoder_length=max_encoder_length,
    max_encoder_length=max_encoder_length,
    min_prediction_length=max_prediction_length,
    max_prediction_length=max_prediction_length,
    time_varying_unknown_reals=["value"],
    time_varying_known_categoricals=["_hour_of_day","_day_of_week","_day_of_month","_day_of_year","_week_of_year","_year" ],
    time_varying_known_reals=["time_idx"],
    add_relative_time_idx=False,
    randomize_length=None,
    scalers=[],
    target_normalizer=TorchNormalizer(method="identity",center=False,transformation=None )

)

validation = TimeSeriesDataSet.from_dataset(
    training,
    data.iloc[-620:-420],
    # predict=True,
    stop_randomization=True,
)       


batch_size = 64
train_dataloader = training.to_dataloader(train=True, batch_size=batch_size, num_workers=8)
val_dataloader = validation.to_dataloader(train=False, batch_size=batch_size, num_workers=8)


# save datasets
training.save("training.pkl")
validation.save("validation.pkl")


early_stop_callback = EarlyStopping(monitor="val_loss", min_delta=1e-4, patience=5, verbose=False, mode="min")
lr_logger = LearningRateMonitor()


trainer = pl.Trainer(
    max_epochs=10,
    gpus=0,
    gradient_clip_val=0.1,
    limit_train_batches=30,
    limit_val_batches=3,
    # fast_dev_run=True,
    # logger=logger,
    # profiler=True,
    callbacks=[lr_logger, early_stop_callback],
)


deepar = DeepAR.from_dataset(
    training,
    learning_rate=0.1,
    hidden_size=32,
    dropout=0.1,
    loss=NegativeBinomialDistributionLoss(),
    log_interval=10,
    log_val_interval=3,
    # reduce_on_plateau_patience=3,
)
print(f"Number of parameters in network: {deepar.size()/1e3:.1f}k")



torch.set_num_threads(10)
trainer.fit(
    deepar,
    train_dataloaders=train_dataloader,
    val_dataloaders=val_dataloader,
)

Answer 1

需要将示例转换为torch.tensor，如下所示。然后保存这个base_metrics.py并重新运行上面的代码。

    except NotImplementedError:  # resort to derive quantiles empirically
           samples = torch.sort(self.sample(y_pred, n_samples), -1).values
           quantiles = torch.quantile(torch.tensor(samples), torch.tensor(quantiles, device=samples.device), dim=2).permute(1, 2, 0)
  return quantiles