tensorflow / tensorflow/models

too slow when Quantization-aware training ssd mobiletnet v2

Open
#6,909 9 comments 0 reactions 2 assignees View on GitHub

@suharshs is already working on this.

Since Jul 11, 2019.

comp:lite models:research
Dominant language
Python
Stars
77.7k
Forks
44.8k
PR merge metrics
No merged PRs in 30d

Description

use ssdlite_mobilenet_v2_coco.config
and modify it by adding graph_rewriter

graph_rewriter { quantization { delay: 0 weight_bits: 8 activation_bits: 8 } }
but the time of each step is 10x slower than the config without graph_rewriter

the log without graph_rewriter

INFO:tensorflow:global step 199709: loss = 1.4051 (0.745 sec/step)
INFO:tensorflow:global step 199710: loss = 1.5033 (0.564 sec/step)
INFO:tensorflow:global step 199710: loss = 1.5033 (0.564 sec/step)
INFO:tensorflow:global step 199711: loss = 1.7374 (1.093 sec/step)
INFO:tensorflow:global step 199711: loss = 1.7374 (1.093 sec/step)
INFO:tensorflow:global step 199712: loss = 1.6265 (0.812 sec/step)

the log with graph_rewiter

INFO:tensorflow:global step 4554: loss = 9.3010 (4.084 sec/step)
INFO:tensorflow:global step 4554: loss = 9.3010 (4.084 sec/step)
INFO:tensorflow:global step 4555: loss = 8.2835 (4.055 sec/step)
INFO:tensorflow:global step 4555: loss = 8.2835 (4.055 sec/step)
INFO:tensorflow:global step 4556: loss = 8.0293 (4.060 sec/step)
INFO:tensorflow:global step 4556: loss = 8.0293 (4.060 sec/step)

the tensorflow-gpu version is 1.12.
is the speed normal, any idea for this?

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.