我如何错误地使用 SubsetRandomSampler？

原文标题 ：How am i incorrectly using SubsetRandomSampler?

我有一个自定义数据集：rcvdataset = rcvLSTMDataSet(‘foo.csv’, ‘foolabels.csv’)

我还定义了以下内容：

batch_size = 50
validation_split = .2
shuffle_rcvdataset = True
random_seed= 42


```
rcvdataset_size = len(rcvdataset)
indices = list(range(rcvdataset_size))
split = int(np.floor(validation_split * rcvdataset_size))
if shuffle_rcvdataset :
    np.random.seed(random_seed)
    np.random.shuffle(indices)
train_indices, val_indices = indices[split:], indices[:split]


train_sampler = SubsetRandomSampler(train_indices)
test_sampler = SubsetRandomSampler(val_indices)

train_loader = torch.utils.data.DataLoader(rcvdataset, batch_size=batch_size, 
                                           sampler=train_sampler)
test_loader = torch.utils.data.DataLoader(rcvdataset, batch_size=batch_size,
                                                sampler=test_sampler)
```

使用此培训电话：

```
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    model.train()
    for batch, (X, y) in enumerate(dataloader):
        X, y = X.to(device), y.to(device)

        # Compute prediction error
        pred = model(X)
        loss = loss_fn(pred, y)

        # Backpropagation
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch % 100 == 0:
            loss, current = loss.item(), batch * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")
```

但是当我尝试运行它时，我得到：

    Epoch 1
    -------------------------------
    Traceback (most recent call last):
      File "lstmTrainer.py", line 94, in <module>
        train(train_sampler, model, loss_fn, optimizer)
      File "lstmTrainer.py", line 58, in train
        size = len(dataloader.dataset)
    AttributeError: 'SubsetRandomSampler' object has no attribute 'dataset'

如果我改为间接加载数据集：

    train(train_loader, model, loss_fn, optimizer)

它告诉我：

    TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'pandas.core.series.Series'>

我根本不清楚第一个错误是什么。第二个错误是否试图告诉我数据集中的某个地方不是张量？

谢谢你。

根据要求，这里是 rcvDataSet.py：

from __future__ import print_function, division
import os
import torch
import pandas as pd
import numpy as np
from torch.utils.data import Dataset, DataLoader
class rcvLSTMDataSet(Dataset):
    """rcv dataset."""
    TIMESTEPS = 10

    def __init__(self, csv_data_file, annotations_file):
        """
        Args:
            csv_data_file (string): Path to the csv file with the training data
            annotations_file (string): Path to the file with the annotations
            
        """
        
        self.csv_data_file = csv_data_file
        self.annotations_file = annotations_file
        self.labels = pd.read_csv(annotations_file)
        self.data = pd.read_csv(csv_data_file)
        

    def __len__(self):
        return len(self.labels)

    def __getitem__(self, idx):
        """
        pytorch expects whatever data is returned is in the form of a tensor.  Included, it expects the label for the data.
        Together, they make a tuple.          
        """
        
        # convert every ten indexes and label into one observation
        Observation = []
        counter = 0
        start_pos = self.TIMESTEPS *idx
        avg_1 = 0
        avg_2 = 0
        avg_3 = 0
        while counter < self.TIMESTEPS:
            Observation.append(self.data.iloc[idx + counter])            
            avg_1 += self.labels.iloc[idx + counter][2]
            avg_2 += self.labels.iloc[idx + counter][1]
            avg_3 += self.labels.iloc[idx + counter][0]
            counter += 1        
        
        avg_1 = avg_1 / self.TIMESTEPS
        avg_2 = avg_2 / self.TIMESTEPS
        avg_3 = avg_3 / self.TIMESTEPS
        current_labels = [avg_1, avg_2, avg_3]
        print(current_labels)
        return Observation, current_labels
        

def main():
        loader = rcvLSTMDataSet('foo1.csv','foo2.csv')
        j = 0
        while j < len(loader.data % loader.TIMESTEPS):
            print(loader.__getitem__(j))
            j += 1

if "__main__" == __name__:
    main()