awslabs / aws-cv-unique-information
We define and estimate smooth unique information of samples with respect to classifier weights and predictions. We compute these quantities for linearized neural networks.
Summary
 |
|||
| Main Code: 3,247 LOC (25 files) = PY (100%) | |||
| Duplication: 31% | |||
| File Size: 0% long (>1000 LOC), 54% short (<= 200 LOC) | |||
| Unit Size: 14% long (>100 LOC), 30% short (<= 10 LOC) | |||
| Conditional Complexity: 0% complex (McCabe index > 50), 54% simple (McCabe index <= 5) | |||
|
|
Logical Component Decomposition: primary (4 components) | ||
|
|
1 year, 4 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
3 files |
|||
Latest commit date: 2021-03-09
|
0
commits
(30 days)
0
contributors
(30 days) |
|