microsoft/nni

Does ProxylessNas implementation really support optimizing inference latency?

Open

#3 113 ouverte le 22 nov. 2020

Voir sur GitHub
 (1 commentaire) (0 réactions) (1 assigné)Python (1 830 forks)batch import
NAShelp wantednew featureuser raised

Métriques du dépôt

Stars
 (13 504 stars)
Métriques de merge PR
 (Aucune PR mergée en 30 j)

Description

Environment:

  • NNI version: v1.9 (including current master)
  • NNI mode (local|remote|pai):
  • Client OS:
  • Server OS (for remote mode only):
  • Python version:
  • PyTorch/TensorFlow version:
  • Is conda/virtualenv/venv used?:
  • Is running in Docker?:

Log message:

  • nnimanager.log:
  • dispatcher.log:
  • nnictl stdout and stderr:

What issue meet, what's expected?:

The most important feature of ProxylessNas is that it can balance deployment latency and accuracy with simple regularization parameters. But this feature is clearly missing in nni. I only found loss = criterion(outputs, labels) and loss.backward() where the criterion is just a cross-entropy loss and only applicable for image classification.

Would nni team consider adding this feature? If not, would you mind I writing this feature and pulling a request?

How to reproduce it?:

Additional information:

Guide contributeur