facebookresearch / higher
higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
Summary
 |
|||
| Main Code: 1,218 LOC (5 files) = PY (100%) | |||
| Duplication: 15% | |||
| File Size: 0% long (>1000 LOC), 14% short (<= 200 LOC) | |||
| Unit Size: 0% long (>100 LOC), 42% short (<= 10 LOC) | |||
| Conditional Complexity: 0% complex (McCabe index > 50), 36% simple (McCabe index <= 5) | |||
|
|
Logical Component Decomposition: primary (2 components) | ||
|
|
2 years, 3 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: 2021-10-26
|
0
commits
(30 days)
0
contributors
(30 days) |
|