Megvii-BaseDetection / Megvii-BaseDetection/BEVDepth

Memory Peak

Open
#174 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
881
Forks
124
PR merge metrics
No merged PRs in 30d

Description

Dear author,

Upon executing the training command, I have observed a phenomenon wherein the memory initially increases to 24GB and subsequently decreases to 15GB before the training process starts.

BEVDepth_memory_bump (1)

I am seeking your insights in understanding the underlying cause behind this memory peak during the initial stage of the process.
Thank you for your time.

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

The issue does not name a file, test, or exact training command. Start by identifying the command and configuration used, then reproduce the reported memory pattern while inspecting startup and training initialization. Done means documenting the cause and confirming whether the peak is expected or requires a targeted change.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.