python - 参数组合无效 - eq()

Question

我正在使用共享代码 here测试 CNN 图像分类器。当我调用测试函数时，我在 line 155 上收到此错误:

test_acc += torch.sum(prediction == labels.data)
TypeError: eq() received an invalid combination of arguments - got (numpy.ndarray), but expected one of:
 * (Tensor other)
      didn't match because some of the arguments have invalid types: ([31;1mnumpy.ndarray[0m)
 * (Number other)
      didn't match because some of the arguments have invalid types: ([31;1mnumpy.ndarray[0m)

test 函数的片段:

def test():
    model.eval()
    test_acc = 0.0
    for i, (images, labels) in enumerate(test_loader):

        if cuda_avail:
                images = Variable(images.cuda())
                labels = Variable(labels.cuda())

        #Predict classes using images from the test set
        outputs = model(images)
        _,prediction = torch.max(outputs.data, 1)
        prediction = prediction.cpu().numpy()
        test_acc += torch.sum(prediction == labels.data) #line 155



    #Compute the average acc and loss over all 10000 test images
    test_acc = test_acc / 10000

return test_acc

经过快速搜索，我发现该错误可能与预测和标签之间的比较有关，如SO question所示.

知道如何解决这个问题吗？

Answer 1

为什么这里有 .numpy() prediction = Prediction.cpu().numpy()？这样您就可以将 PyTorch 张量转换为 NumPy 数组，使其与 labels.data 进行比较时的类型不兼容。

删除 .numpy() 部分应该可以解决问题。