Mobile Neural Network (MNN) is a mobile inference engine tailored to mobile applications. The contributions of MNN include: (1) presenting a mechanism called pre-inference that manages to conduct runtime optimization; (2) delivering thorough kernel optimization on operators to achieve optimal computation performance; (3) introducing backend abstraction module which enables hybrid scheduling and keeps the engine lightweight.
Source: MNN: A Universal and Efficient Inference EnginePaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Color Manipulation | 1 | 25.00% |
Image Enhancement | 1 | 25.00% |
Photo Retouching | 1 | 25.00% |
Tone Mapping | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |