facebookresearch / fisher_information_loss
This code reproduces the results of the paper, "Measuring Data Leakage in Machine-Learning Models with Fisher Information"
Summary
 |
|||
| Main Code: 1,385 LOC (8 files) = PY (100%) Secondary code: Test: 173 LOC (1); Generated: 0 LOC (0); Build & Deploy: 138 LOC (1); Other: 81 LOC (3); |
|||
| Duplication: 8% | |||
| File Size: 0% long (>1000 LOC), 43% short (<= 200 LOC) | |||
| Unit Size: 0% long (>100 LOC), 37% short (<= 10 LOC) | |||
| Conditional Complexity: 0% complex (McCabe index > 50), 43% simple (McCabe index <= 5) | |||
|
|
Logical Component Decomposition: primary (2 components) | ||
|
|
11 months old
|
||
|
|
0% of code updated more than 50 times Also see temporal dependencies for files frequently changed in same commits. |
||
| Goals: Keep the system simple and easy to change (4) | |||
|
Features of interest:
TODOs
1 file |
|||
Latest commit date: 2021-08-17
|
0
commits
(30 days)
0
contributors
(30 days) |
|