tensorflow / tensorflow/model-optimization

Pruning does not reduce inference time.

Open
#611 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature request
Dominant language
Python
Stars
1.6k
Forks
349
Avg merge
3d 2h
Merged PRs (30d)
1

Description

System information

  • TensorFlow version (you are using): 2.3.0
  • Are you willing to contribute it (Yes/No): No

Motivation
Currently pruning in tensorflow_model_optimization  does not result in a reduction in inference time. Even though the pruned model is sparser than the original, the inference time remains the same. (This was tested on a Resnet model.)

Describe the feature  Pruning sets the weights to zero, but does not prune the networks edges. Update the pruning feature such that the new sparse weights result in a corresponding increase in speed. 

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the pruning feature in tensorflow_model_optimization and reproduce the reported behavior with a ResNet model. Investigate how sparse weights are represented and whether they affect inference execution. Done means pruning produces a measurable inference-time reduction rather than only zero-valued weights.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, tensorflow
Domain
machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.