Closed hehaiyang111 closed 3 years ago
Maybe you can refer to https://pytorch.org/tutorials/beginner/transfer_learning_tutorial.html.
but, acc 0.1 + why? Thanks bro.
Is the pre-trained model trained on ImageNet or other?
The pre-trained ResNet-50 is trained on ImageNet.
Maybe batchsize 4 is too small to train a model. We use 256 batchsize to train our AdderNet on ImageNet.
hi, How does transfer learning train its own data set to modify pre-training parameters? thanks