facebookresearch / TimeSformer
The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"
Summary
  |
|||
| Main Code: 9,984 LOC (86 files) = PY (92%) + YAML (7%) + YML (<1%) + CFG (<1%) Secondary code: Test: 124 LOC (1); Generated: 0 LOC (0); Build & Deploy: 10 LOC (2); Other: 305 LOC (6); |
|||
| Duplication: 20% | |||
| File Size: 0% long (>1000 LOC), 41% short (<= 200 LOC) | |||
| Unit Size: 9% long (>100 LOC), 46% short (<= 10 LOC) | |||
| Conditional Complexity: 5% complex (McCabe index > 50), 56% simple (McCabe index <= 5) | |||
|
|
Logical Component Decomposition: primary (10 components) | ||
|
|
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) | |||
|
Features of interest:
TODOs
3 files |
|||
Latest commit date: 2021-05-28
|
0
commits
(30 days)
0
contributors
(30 days) |
|