Horovod
Horovod is a distributed training framework for TensorFlow, Keras, PyTorch, and MXNet.
Summary
| Main Code: 27,121 LOC = PY (51%) + CC (33%) + H (14%) + RST (<1%) | ... | ||
| Duplication: 15% | ... | ||
| File Size: 0% long (>1000 LOC), 49% short (<= 200 LOC) | ... | ||
| Unit Size: 6% long (>100 LOC), 51% short (<= 20 LOC) | ... | ||
| Conditional Complexity: 3% complex (McCabe index > 25), 59% simple (McCabe index <= 5) | ... | ||
|
|
Logical Component Decomposition: primary (14 components) | ... | |
|
|
3 years, 1 month old
|
... | |
| Goals: Keep the system simple and easy to change (4) | ... |
Contributors (94)
Recent Contributors (37 = 9 veterans + 28 rookies)
Contributed in past 6 months (a rookie = the first contribution in past year)
Past 30 days (11):
Past 31 to 90 days (10):
Past 91 to 180 days (16):
Historical Contributors (57)
Last contributed more than 6 months ago
Trend
| Commits |
25 |
104 |
234 |
239 |
| Contributors |
3 |
19 |
49 |
43 |
| 2017 | 2018 | 2019 | 2020 |
Reports
Analysis Report
Features of Interest
Analysis Report
Trend
Analysis Report
Notes & Findings