In the Cifar10 image classifier example, what are the classes that performed well, and the classes did not perform well.
firstly, set the constant:
N_CLASSES
BATCH_SIZE
classes = ('plane', 'car', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
class_correct = list(0. for i in range(N_CLASSES))
class_total = list(0. for i in range(N_CLASSES))
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predicted = torch.max(outputs, 1)
c = (predicted == labels).squeeze()
for i in range(BATCH_SIZE):
label = labels[i]
class_correct[label] += c[i].item()
class_total[label] += 1
for i in range(N_CLASSES):
print('Accuracy of %5s : %2d %%' % (
classes[i], 100 * class_correct[i] / class_total[i]))
Very clever codes from the official cite.