在分类模型测试代码中有以下代码段:
correct = 0
total = 0
# since we're not training, we don't need to calculate the gradients for our outputs
with torch.no_grad():
for data in testloader:
images, labels = data
# calculate outputs by running images through the network
outputs = net(images)
# the class with the highest energy is what we choose as prediction
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: %d %%' % (
100 * correct / total))
其中:
dataiter = iter(test_dataloader)
images, labels = dataiter.next()
print(labels)
print(f"label.size()返回: {labels.size()} \n type: {type(labels.size())}")
print(f"label.size(0)返回: {labels.size(0)} \n type: {type(labels.size(0))}")
tensor([3, 8, 8, 0])
>>>label.size()返回: torch.Size([4])
>>> type: <class 'torch.Size'>
>>>label.size(0)返回: 4
>>> type: <class 'int'>