Megvii-BaseDetection / Megvii-BaseDetection/DynamicRouting

Where and how to calculate FLOPs

Open
#41 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
380
Forks
45
PR merge metrics
No merged PRs in 30d

Description

Hello, although I'm researching in a different area, I was inspired by your article and want to try incorporating FLOPs into the calculation of the loss function. In your code, where exactly is the method for calculating FLOPs, as shown in the figure below?
图片

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

Start by searching the Python source for FLOPs-related calculations and the loss-function entry points. Trace how the calculation shown in the linked figure would connect to training, then document the relevant location and usage. Done means the repository identifies where FLOPs are calculated or confirms that the method is absent.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.