lucidrains / lucidrains/lambda-networks
why flops so high?
Open
- 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