facebookresearch / Motionformer
Code + pre-trained models for the paper Keeping Your Eye on the Ball Trajectory Attention in Video Transformers
Summary
   |
|||
| Main Code: 10,947 LOC (89 files) = PY (81%) + YAML (14%) + HTML (3%) + YML (<1%) + CFG (<1%) Secondary code: Test: 162 LOC (1); Generated: 0 LOC (0); Build & Deploy: 91 LOC (3); Other: 318 LOC (4); |
|||
| Duplication: 27% | |||
| File Size: 0% long (>1000 LOC), 44% short (<= 200 LOC) | |||
| Unit Size: 5% long (>100 LOC), 41% short (<= 10 LOC) | |||
| Conditional Complexity: 5% complex (McCabe index > 50), 54% simple (McCabe index <= 5) | |||
|
|
Logical Component Decomposition: primary (14 components) | ||
|
|
7 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
2 files |
|||
Latest commit date: 2021-10-19
|
0
commits
(30 days)
0
contributors
(30 days) |
|