facebookresearch / Augur

Augur is a machine learning system that provides per-layer inference performance and energy cost of running a NN layer on a consumer grade commercial NN accelerator.

Summary
email_034-attachment-send-file-code-cssCreated with Sketch.
Main Code: 122 LOC (1 files) = PY (100%)
Secondary code: Test: 0 LOC (0); Generated: 0 LOC (0); Build & Deploy: 0 LOC (0); Other: 107 LOC (6);
File Size: 0% long (>1000 LOC), 100% short (<= 200 LOC)
Logical Component Decomposition: primary (1 component)
Goals: Keep the system simple and easy to change (4)
Reports
Analysis Report
files_time
File Age
Analysis Report
File Change Frequency
Analysis Report
Temporal Dependencies
Analysis Report
Contributors
Analysis Report
Unit Size
Analysis Report
Conditional Complexity
Analysis Report
Trend
Analysis Report
76_startup_sticky_notes
Notes & Findings
Links

generated by sokrates.dev (configuration) on 2022-01-25