Re-Training after pruning


I have a question so, does the re-training of a pruned tlt model have any effect on the pruned model or does the re-training bring up the original network structure?

Thank you!

For detectnet_v2 retraining, see DetectNet_v2 — TAO Toolkit 3.21.11 documentation


My answer is not mentioned in the document.

To regain the accuracy.

The pruning is to remove parameters from the model to reduce the model size without compromising the integrity of the model.

does the re-training add those parameters back or the removed parameters remains the same?

The retraining will not add parameters back.


Thank you!

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.