AttributeError: 'list' object has no attribute 'dim' when trying to predict

Hi, here is my code:

# coding: utf-8

# In[5]:

import torch
import torchvision
from torchvision import transforms, datasets
import torch.nn as nn
import torch.nn.functional as F
import as utils
import numpy as np

data_np = np.loadtxt('input_preds.csv', delimiter=',')

train_ds = utils.TensorDataset(torch.tensor(data_np, dtype=torch.float32).view(-1,11))

trainset =, batch_size=1, shuffle=True)

# setting device on GPU if available, else CPU, replace .cuda() with .to(device)
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

class Net(nn.Module):
    def __init__(self):
        super().__init__() = nn.BatchNorm2d(11)
        self.fc1 = nn.Linear(11, 22)
        self.fc2 = nn.Linear(22, 44)
        self.fc3 = nn.Linear(44, 22)
        self.fc4 = nn.Linear(22, 11)

    def forward(self, x):
        #x = x.view(-1, 11)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = F.relu(self.fc3(x))
        x = self.fc4(x)
        #return F.log_softmax(x, dim=1)
        return x
model1 = torch.load('./1e-2')
model2 = torch.load('./1e-3')

for data in trainset:   
        X = data  
        X = X
        output = model1(X).to(device)

I’m currently loading 11 values from a csv, converting the values into a tensor, and trying to predict the output values. Also, I’m loading a pretrained model. However, I get this error:

Traceback (most recent call last):
  File "", line 53, in <module>
    output = model1(X).to(device)
  File "C:\Users\Happy\Miniconda3\envs\torch\lib\site-packages\torch\nn\modules\", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "", line 40, in forward
    x = F.relu(self.fc1(x))
  File "C:\Users\Happy\Miniconda3\envs\torch\lib\site-packages\torch\nn\modules\", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "C:\Users\Happy\Miniconda3\envs\torch\lib\site-packages\torch\nn\modules\", line 55, in forward
    return F.linear(input, self.weight, self.bias)
  File "C:\Users\Happy\Miniconda3\envs\torch\lib\site-packages\torch\nn\", line 1022, in linear
    if input.dim() == 2 and bias is not None:
AttributeError: 'list' object has no attribute 'dim'

How do I fix this error? Is it an error with the prediction or the model definition? Thank you for your help.

Pass the data as model1(X[0]) into your model.
Although you are only dealing with a data tensor (without a target tensor), data will be a list object.
Unfortunately, dropping the missing target via for data, _ in trainset won’t work, and I think this might be due to the implementation of TensorDataset.

If you use this custom implementation:

class MyDataset(Dataset):
    def __init__(self, data): = data
    def __getitem__(self, index):
        x =[index]
        return x
    def __len__(self):
        return len(

train_ds = MyDataset(torch.from_numpy(data_np).float().view(-1, 11))

your training loop will work as expected.