tensorflow / tensorflow/models

Performance numbers on TF1 OD and TF2 OD

Open
#10,205 2 comments 0 reactions 3 assignees View on GitHub

@pkulzc is already working on this.

Since Aug 12, 2021.

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

Description

Prerequisites

Please answer the following question for yourself before submitting an issue.

  • I checked to make sure that this issue has not been filed already.

1. The entire URL of the documentation with the issue

https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md
https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf1_detection_zoo.md

2. Describe the issue

I've been trying to compare the performance numbers on TF1 and TF2 OD. I'm not sure if any of the models in both are same but lets take 'faster_rcnn_resnet101_coco' for instance in TF1 OD (106ms) and 'Faster R-CNN ResNet101 V1 640x640' in TF2 OD (55ms). Why is there such a huge difference? Also It is clearly documented in TF1 OD that the results are based on Nvidia GeForce GTX TITAN X. But TF2 OD does not have any details listed.

Moreover, when I tested them I didn't get much difference in their execution speed (about 7-8 FPS in both). Please help me understand the discrepancy.

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.