facebookresearch / dino
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
Summary
 |
|||
| Main Code: 2,724 LOC (12 files) = PY (100%) Secondary code: Test: 0 LOC (0); Generated: 0 LOC (0); Build & Deploy: 0 LOC (0); Other: 360 LOC (1); |
|||
| Duplication: 4% | |||
| File Size: 0% long (>1000 LOC), 24% short (<= 200 LOC) | |||
| Unit Size: 11% long (>100 LOC), 42% short (<= 10 LOC) | |||
| Conditional Complexity: 6% complex (McCabe index > 50), 53% simple (McCabe index <= 5) | |||
|
|
Logical Component Decomposition: primary (1 component) | ||
|
|
9 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) | |||
Latest commit date: 2021-10-05
|
0
commits
(30 days)
0
contributors
(30 days) |
|