Ziri

Hi everyone , I saw many example of visualizing CAM with python using "register_backward_hook" but can't find any way to do the same in C++ frontend. Is there away to...

Regarding the execution speed and model size after Sparsifying ResNet-50

1

I tried the same Methode described in : https://github.com/neuralmagic/sparseml/blob/main/integrations/torchvision/tutorials/docs-torchvision-sparsify-from-scratch-resnet50-beans.ipynb with the same recipe files and here are my results: *dense Val Loss: 0.03551835000926499 Top 1 Acc: 0.9824561403508771 model size: 89.895MB...

How to add accuracy metric ?

1

Hi AllentDan, Can you please explain how to add the accuracy metric in the training loop ? Thank you.

What are the Prediction Input Masks ?

1

This is not an issue , I am just confused about the meaning of the input masks you are using in prediction . do you provide the actual mask of...

I used your test code from the " High-level Pruners" section in the documentation: Instead of using "resnet18" I used resnet50 on an easy classification task. the accuracy without pruning...