IniziaInizia gratis

Finalize pruning by removing the mask

After pruning a model, you need to finalize it before saving or deploying. This means removing the pruning mask so the model no longer tracks which weights were zeroed. You'll use prune.remove() to complete this step.

Questo esercizio fa parte del corso

Scalable AI Models with PyTorch Lightning

Visualizza il corso

Istruzioni dell'esercizio

  • Finalize the pruning of the weight parameter.
  • Use prune.remove() to remove the mask and store the final weights.
  • Print the model to confirm pruning removal.

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

import torch.nn.utils.prune as prune
# Before pruning
print(model)
# Finalize pruning by removing the pruning mask
prune.____(model[3], "____")
# Print model structure after pruning
print(____)
Modifica ed esegui il codice