This repository contains a Pytorch implementation of the paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" by Jonathan Frankle and Michael Carbin that can be easily adapted to any model/dataset.
Can you give a hint on the expected runtime or parameter settings?
I am trying to prune a VGG16 with the CIFAR10 dataset using the command below. I have started the training 6 hours ago, but it is only at 37% accuracy and 0% pruning. I guess the parameters need to be adjusted? Maybe you have a hint?
Can you give a hint on the expected runtime or parameter settings?
I am trying to prune a VGG16 with the CIFAR10 dataset using the command below. I have started the training 6 hours ago, but it is only at 37% accuracy and 0% pruning. I guess the parameters need to be adjusted? Maybe you have a hint?
python3 main.py --prune_type=lt --arch_type=vgg16 --dataset=cifar10 --prune_percent=10 --prune_iterations=35