Accuracy drop after simplify

Hi guys, thank you for your library. It is quite cool.

However, I have met a problem when I try to use Simplify with Resnet18 on CIFAR10 dataset. I have used global_unstructured pruning in Pytorch and the sparsity was set to 0.875. Then I have transfer the weights of a list of neurons in layer4.1.Conv1 (Penultimate layer) to zero. In the next, I implemented the Simplify. The test_acc after “pruning” is 92.6%, after “pruning + transfer neurons’ weight to 0” is 92.24%, after “pruning + transfer neurons’ weight to 0 + simplify” is 92.21%.

I think there was supposed to be no test_acc decrease after the Simplify process. Could you please help me understand what happens here? I hope I have described my problem well.

If you want to reproduce, here is the link of my code and required files.
https://partage.imt.fr/index.php/s/9jemn7WfkBWS5tx

Start with the externally linked reproduction and the reported ResNet18/CIFAR10 workflow, including global_unstructured pruning, layer4.1.Conv1, and Simplify. Compare the three reported accuracy stages and inspect the Simplify entry point; done means explaining the accuracy change or identifying a reproducible correction.

Written by the indexing model from the issue text.