lucidrains / lucidrains/lambda-networks

why flops so high?

Open
#22 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
1.5k
Forks
155
PR merge metrics
No merged PRs in 30d

Description

I used resnet50, and change C4 layer into LambaBottleNeck; but why flops so high about 20G and input size is 224*244; is that right, or something wrong about my inplementation.

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by inspecting the ResNet50 change that replaces the C4 layer with LambdaBottleNeck and the code used to calculate FLOPs. Verify the 224*244 input dimensions and compare the reported 20G value with the expected computation; done means explaining whether the result is correct or identifying an implementation error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning, performance
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.