pytorch / benchmark
TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.
Summary
    |
|||
| Main Code: 55,432 LOC (582 files) = PY (71%) + CFG (21%) + YAML (3%) + IPYNB (2%) + YML (<1%) + M (<1%) + PT (<1%) Secondary code: Test: 1,183 LOC (19); Generated: 0 LOC (0); Build & Deploy: 620 LOC (46); Other: 4,128 LOC (88); |
|||
| Duplication: 39% | |||
| File Size: 0% long (>1000 LOC), 46% short (<= 200 LOC) | |||
| Unit Size: 10% long (>100 LOC), 51% short (<= 10 LOC) | |||
| Conditional Complexity: 5% complex (McCabe index > 50), 61% simple (McCabe index <= 5) | |||
|
|
Logical Component Decomposition: primary (75 components) | ||
|
|
4 years, 6 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
16 files |
|||
Latest commit date: 2022-04-01
Reference analysis date: 2022-04-01
|
38
commits
(30 days)
8
contributors
(30 days) |
|