Open kikyou123 opened 4 years ago
No. Only base classes are used in pre-training. https://github.com/YU1ut/imprinted-weights/blob/master/loader.py#L27 And the network only classifies 100 classes. https://github.com/YU1ut/imprinted-weights/blob/master/models.py#L6
Yes, I understand. Thanks for replying!
I have another question. When you pretrain the model, you set the train loader as :
train_dataset = loader.ImageLoader( args.data, transforms.Compose([ transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ToTensor(), normalize, ]), train=True)
I argue should you insert the transforms.Resize(256),
before transforms.RandomResizedCrop(224),
It seems that you pre-train the model with all the training images, including the base and novel classes. I argue it is unfair to use the novel classes to train the model.