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
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(____)