when should I train it？ about rethinking-network-pruning

[Eric-mingjie]

Prune the model you trained and then finetune.

[hlyj1995]

@Eric-mingjie
Thanks for your reply. If I prune my trained model and finetune it . Isn't this a violation of your paper's idea of retraining using a model with random initial weights?
And I have tried your code, so there is a question, I found some pruning needs to download the pre-training model, are these models randomly weighted?

[Eric-mingjie]

This isn't a violation. Our paper is just saying that training from scratch achieves similar performance as fine-tuning. In practice, fine-tuning is much faster if you have a pre-trained model.

Pre-trained models are not randomly weighted.

[hlyj1995]

This isn't a violation. Our paper is just saying that training from scratch achieves similar performance as fine-tuning. In practice, fine-tuning is much faster if you have a pre-trained model.

Pre-trained models are not randomly weighted.

thanks,i get it