Inference Performance
Back to Home
01. Intro
02. Why Bother With Performance
03. Semantic Segmentation Revisited
04. Interlude: Using The AMI
05. Freezing Graphs
06. Graph Transforms
07. Fusion
08. Optimizing For Inference
09. Reducing Precision
10. Quantization Quiz
11. Quantization Conversion
12. 8-bit Calculations
13. Compilation
14. AOT & JIT
15. Reusing The Graph
16. Outro
Back to Home
02. Why Bother With Performance
Why Bother With Performance
Next Concept