search

aaron-xichen / pytorch-playground

Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)
MIT License
2.62k stars 612 forks source link

quantization with my own model #3

Closed pgadosey closed 7 years ago

pgadosey commented 7 years ago

Hi, I have a modified vgg16 model. How do I specify that in the type flag for quantize.py given that I have my own path where my model is located.

aaron-xichen commented 7 years ago

Sorry for that maybe you need to modify quantize.py. To load your model and dataset, following the code from line 48 to line 94 in quantize.py

pgadosey commented 7 years ago

okay, got it. thank you