ValueError: only one element tensors can be converted to Python scalars

Question

I'm following this tutorial.

I'm at the last part where we combine the models in a regression.

I'm coding this in jupyter as follows:

import shutil
import os
import time
from datetime import datetime
import argparse
import pandas
import numpy as np
from tqdm import tqdm
from tqdm import tqdm_notebook

import torch
import torch.nn as nn
import torch.optim as optim
from torch.autograd import Variable
from torchsample.transforms import RandomRotate, RandomTranslate, RandomFlip, ToTensor, Compose, RandomAffine
from torchvision import transforms
import torch.nn.functional as F
from tensorboardX import SummaryWriter

import dataloader
from dataloader import MRDataset
import model

from sklearn import metrics

def extract_predictions(task, plane, train=True):
    assert task in ['acl', 'meniscus', 'abnormal']
    assert plane in ['axial', 'coronal', 'sagittal']
    
    models = os.listdir('models/')

    model_name = list(filter(lambda name: task in name and plane in name, models))[0]
    model_path = f'models/{model_name}'

    mrnet = torch.load(model_path)
    _ = mrnet.eval()
    
    train_dataset = MRDataset('data/', 
                              task, 
                              plane, 
                              transform=None, 
                              train=train, 
                              )
    
    train_loader = torch.utils.data.DataLoader(train_dataset, 
                                               batch_size=1, 
                                               shuffle=False, 
                                               num_workers=10, 
                                               drop_last=False)
    predictions = []
    labels = []
    with torch.no_grad():
        for image, label, _ in tqdm_notebook(train_loader):
            logit = mrnet(image.cuda())
            prediction = torch.sigmoid(logit)
            predictions.append(prediction.item())
            labels.append(label.item())

    return predictions, labels

task = 'acl'
results = {}

for plane in ['axial', 'coronal', 'sagittal']:
    predictions, labels = extract_predictions(task, plane)
    results['labels'] = labels
    results[plane] = predictions
    
X = np.zeros((len(predictions), 3))
X[:, 0] = results['axial']
X[:, 1] = results['coronal']
X[:, 2] = results['sagittal']

y = np.array(labels)

logreg = LogisticRegression(solver='lbfgs')
logreg.fit(X, y)

task = 'acl'
results_val = {}

for plane in ['axial', 'coronal', 'sagittal']:
    predictions, labels = extract_predictions(task, plane, train=False)
    results_val['labels'] = labels
    results_val[plane] = predictions

y_pred = logreg.predict_proba(X_val)[:, 1]
metrics.roc_auc_score(y_val, y_pred)

However I get this error:

ValueError                                Traceback (most recent call last)
<ipython-input-2-979acb314bc5> in <module>
      3 
      4 for plane in ['axial', 'coronal', 'sagittal']:
----> 5     predictions, labels = extract_predictions(task, plane)
      6     results['labels'] = labels
      7     results[plane] = predictions

<ipython-input-1-647731b6b5c8> in extract_predictions(task, plane, train)
     54             logit = mrnet(image.cuda())
     55             prediction = torch.sigmoid(logit)
---> 56             predictions.append(prediction.item())
     57             labels.append(label.item())
     58 

ValueError: only one element tensors can be converted to Python scalars

Here's the MRDataset code in case:

class MRDataset(data.Dataset):
    def __init__(self, root_dir, task, plane, train=True, transform=None, weights=None):
        super().__init__()
        self.task = task
        self.plane = plane
        self.root_dir = root_dir
        self.train = train
        if self.train:
            self.folder_path = self.root_dir + 'train/{0}/'.format(plane)
            self.records = pd.read_csv(
                self.root_dir + 'train-{0}.csv'.format(task), header=None, names=['id', 'label'])
        else:
            transform = None
            self.folder_path = self.root_dir + 'valid/{0}/'.format(plane)
            self.records = pd.read_csv(
                self.root_dir + 'valid-{0}.csv'.format(task), header=None, names=['id', 'label'])

        self.records['id'] = self.records['id'].map(
            lambda i: '0' * (4 - len(str(i))) + str(i))
        self.paths = [self.folder_path + filename +
                      '.npy' for filename in self.records['id'].tolist()]
        self.labels = self.records['label'].tolist()

        self.transform = transform
        if weights is None:
            pos = np.sum(self.labels)
            neg = len(self.labels) - pos
            self.weights = torch.FloatTensor([1, neg / pos])
        else:
            self.weights = torch.FloatTensor(weights)

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

    def __getitem__(self, index):
        array = np.load(self.paths[index])
        label = self.labels[index]
        if label == 1:
            label = torch.FloatTensor([[0, 1]])
        elif label == 0:
            label = torch.FloatTensor([[1, 0]])

        if self.transform:
            array = self.transform(array)
        else:
            array = np.stack((array,)*3, axis=1)
            array = torch.FloatTensor(array)

        # if label.item() == 1:
        #     weight = np.array([self.weights[1]])
        #     weight = torch.FloatTensor(weight)
        # else:
        #     weight = np.array([self.weights[0]])
        #     weight = torch.FloatTensor(weight)

        return array, label, self.weights

I've only trained my models using 1 and 2 epochs for each plane of the MRI instead of 35 as in the tutorial, not sure if that has anything to do with it. Other than that I'm stranded as to what this could be? I also removed normalize=False in the options for train_dataset as it kept giving me an error and I read that it could be removed, but I'm not so sure?

Answer 1

Only a tensor that contains a single value can be converted to a scalar with item(), try printing the contents of prediction, I imagine this is a vector of probabilities indicating which label is most likely. Using argmax on prediction will give you your actual predicted label (assuming your labels are 0-n).