tensorflow / tensorflow/tflite-support

Same RAM usage TFlite model on Xavier and CPU Laptop

Open
#791 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
441
Forks
146
PR merge metrics
No merged PRs in 30d

Description

Hi all,
I am working on optimization. I have a .h5 keras model named "model.h5" --> I pruned this model to become a smaller and slighter model named "pruned_model.h5". I converted 2 models to tflite (model.tflite and pruned_model.tflite). When I inference 2 models on CPU Laptop and Xavier.
--> problem: The RAM usage is the same among models.
I think a slighter model if convert to tflite will use less RAM than bigger model ?
I also think about tf.config.experimental.set_memory_growth(gpu, True) of tensorflow, but it doesn't affect tflite model.
Any help ?
Thank you so much

Contributor guide

No contributing guide indexed for this repository

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

No repository file or test is identified; start by reproducing inference with model.tflite and pruned_model.tflite on the CPU laptop and Xavier while measuring process RAM. Compare the two runs and document whether the issue is runtime allocation or model size, with a clear explanation of the observed behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
keras, tensorflow
Domain
embedded-iot, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.