Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)
2.62k
stars
612
forks
source link
Why does your model return 2 acc in the quantize script? #62
Open
Yas-bonfim opened 1 year ago
I executed quantization with MNIST dataset. After that, it returns acc1 and acc5. What's the difference between them? Why do you use them?