Every commit scored for change-risk against this repo's own history, so 'elevated' means elevated here rather than on some global curve.
Needs review
52 commits sit in this repo's top risk tercile, which is 33% of the 157scored. The cut is drawn against this codebase's own history rather than a global curve, so a quiet repo still fills its top band, and here it starts at 3.3 out of 10. What pushes a commit up is size and spread together: a large change confined to one area scores below a smaller one scattered across a dozen files.
Commit categories over time, read off the subject line. Fixes carry the accent because that is the series this chart exists to show.
Began docs-led, now leaning other.
Ranked by change-risk, highest first. Priority is a tercile of this repo's own distribution, so a quiet repo still fills its top band.
| # | Commit | Author | When | Lines | Risk | Top driver |
|---|---|---|---|---|---|---|
| 1 | 54fd9220update image data and model weights | luoyao | 7y ago | +224.2K -4 | 99%Elevated | more lines added than baseline |
| 2 | 1cfe4508upload new model | luoyao | 7y ago | +514.2K -12 | 99%Elevated | more lines added than baseline |
| 3 | deb61b09first commit | luoyao | 8y ago | +2.1K -0 | 98%Elevated | more lines added than baseline |
| 4 | 28438747ignore fix | Banee Ishaque K | 5y ago | +458 -0 | 97%Elevated | more lines added than baseline |
| 5 | 3d477275add context module | luoyao | 7y ago | +538 -0 | 97%Elevated | more lines added than baseline |
| 6 | 7eb4b953update | luoyao | 6y ago | +197 -209 | 96%Elevated | more lines added than baseline |
| 7 | f7a02408add requirement.txt | luoyao | 8y ago | +206 -0 | 96%Elevated | more lines added than baseline |
| 8 | 4154159dAdd files via upload | Banee Ishaque K | 5y ago | +171 -0 | 95%Elevated | more lines added than baseline |
| 9 | 6ffbaa0cuse tf dataset implement data feed pipline | luoyao | 7y ago | +157 -383 | 95%Elevated | more lines added than baseline |
| 10 | f7a6c49bupdate train and test script | luoyao | 7y ago | +264 -514.4K | 94%Elevated | more lines added than baseline |
| 11 | b896910fupdate tensorflow saved model export tools | luoyao | 7y ago | +182 -0 | 93%Elevated | more lines added than baseline |
| 12 | 10911793write readme | luoyao | 8y ago | +108 -1 | 93%Elevated | more lines added than baseline |
| 13 | 3faa579aremode layer normalization function | luoyao | 7y ago | +105 -107 | 92%Elevated | more lines added than baseline |
| 14 | 73c7a88b增加group normalization层 | luoyao | 7y ago | +77 -41 | 92%Elevated | more lines added than baseline |
| 15 | 3d112b14add image random crop augmentation | luoyao | 7y ago | +76 -3 | 91%Elevated | more lines added than baseline |
| 16 | d397b3f2update model weights file | luoyao | 6y ago | +122 -1 | 90%Elevated | more lines added than baseline |
| 17 | 1a86061fupdate | luoyao | 6y ago | +98 -14 | 90%Elevated | more lines added than baseline |
| 18 | c2933f77Format | Banee Ishaque K | 5y ago | +112 -128 | 89%Elevated | more lines added than baseline |
| 19 | 3fcc7fc7对比tensorflow ssim, psnr和skimage ssim, psnr的计算结果 | luoyao | 7y ago | +62 -0 | 89%Elevated | more lines added than baseline |
| 20 | b04ac3acremove bn layer | luoyao | 7y ago | +58 -60 | 88%Elevated | more lines added than baseline |
| 21 | a717e17cadd random flip augmentation function | luoyao | 7y ago | +51 -7 | 87%Elevated | more lines added than baseline |
| 22 | fdb554deGitpod IDE | Banee Ishaque K | 5y ago | +49 -6 | 86%Elevated | more lines added than baseline |
| 23 | abb22f29Create python-app.yml | Banee Ishaque K | 5y ago | +36 -0 | 85%Elevated | more lines added than baseline |
| 24 | d1681febupdate readme | luoyao | 7y ago | +41 -12 | 85%Elevated | more lines added than baseline |
| 25 | f04ec671更新cnn base net, 增加group normalization层 | luoyao | 7y ago | +32 -1 | 84%Elevated | more lines added than baseline |
| 26 | b027e822更新mask生成方式,修改阈值,增加图像形态学计算 | luoyao | 7y ago | +28 -11 | 84%Elevated | more lines added than baseline |
| 27 | 140d6425rename author and site | luoyao | 7y ago | +30 -127 | 83%Elevated | more lines added than baseline |
| 28 | 77192ba4Create LICENSE | MaybeShewill-CV | 7y ago | +21 -0 | 82%Elevated | more lines added than baseline |
| 29 | 7fb1bd0aupdate readme | luoyao | 6y ago | +17 -22 | 82%Elevated | more lines added than baseline |
| 30 | e5eb5265update training code | luoyao | 7y ago | +16 -11 | 81%Elevated | more lines added than baseline |
| 31 | 2c0afc51Gitpod | Banee Ishaque K | 5y ago | +13 -0 | 81%Elevated | more lines added than baseline |
| 32 | 62dff077Conda Env. | Banee Ishaque K | 5y ago | +14 -0 | 80%Elevated | more lines added than baseline |
| 33 | c510c65dupdate README about some common issue | luoyao | 8y ago | +15 -0 | 80%Elevated | more lines added than baseline |
| 34 | e99879b5Add .whitesource configuration file | whitesource-bolt-for-github[bot] | 5y ago | +12 -0 | 78%Elevated | more focused than baseline |
| 35 | 3642fbf2update readme | luoyao | 7y ago | +14 -1 | 78%Elevated | more lines added than baseline |
| 36 | 727e08e1update README | luoyao | 7y ago | +13 -13 | 77%Elevated | more lines added than baseline |
| 37 | a5eec341add image metrics computation | luoyao | 7y ago | +13 -5 | 77%Elevated | more lines added than baseline |
| 38 | 6fac00dcupdate readme | luoyao | 7y ago | +12 -0 | 76%Elevated | more focused than baseline |
| 39 | 75d8946fupdate readme.md | luoyao | 8y ago | +10 -10 | 75%Elevated | more focused than baseline |
| 40 | 88addc7fmodulise | baneeishaque3 | 5y ago | +9 -9 | 75%Elevated | more scattered than baseline |
| 41 | 8168114dAdd .deepsource.toml | DeepSource Bot | 5y ago | +8 -0 | 74%Elevated | fewer lines added than baseline |
| 42 | 4cf3c0eaupdate | luoyao | 6y ago | +10 -0 | 74%Elevated | more focused than baseline |
| 43 | c8a0f75bupdate readme and uploaded a new model | luoyao | 7y ago | +21 -3 | 74%Elevated | more lines added than baseline |
| 44 | ea22ce95pyup fix | Banee Ishaque K | 5y ago | +8 -1 | 72%Elevated | fewer lines added than baseline |
| 45 | 2ca52f40Update requirements.txt | Banee Ishaque K | 5y ago | +8 -8 | 72%Elevated | fewer lines added than baseline |
| 46 | bd8a550bmodified batch size and add cropped size configuration | luoyao | 7y ago | +9 -5 | 72%Elevated | fewer lines added than baseline |
| 47 | 80b113a6update train_model.py | luoyao | 7y ago | +8 -6 | 70%Elevated | fewer lines added than baseline |
| 48 | 04bb6f80modify last output into tanh activation | luoyao | 8y ago | +9 -2 | 70%Elevated | fewer lines added than baseline |
| 49 | 1ae6e33dGitpod | Banee Ishaque K | 5y ago | +7 -0 | 69%Elevated | fewer lines added than baseline |
| 50 | 82dad1dbrename author info | luoyao | 7y ago | +8 -8 | 69%Elevated | fewer lines added than baseline |
Two views of the same model: where the cuts fall, and what commit shape lands you above them.
Every scored commit, binned on the raw 0 to 10 score rather than the percentile. Percentile ranks are uniform by construction, so that axis has no shape to draw. The dashed lines are the tercile cuts behind each row's priority pill.
The 157 most recent commits, on their own recency sample rather than the feed above: that defaults to risk-sorted, so reusing it would plot only the top tercile and call it the spread. Big and scattered is what the model penalises. Click a dot to open it.
baneeishaque/attentive-gan-derainnet has 172 commits in its history from 9 contributors, the first of them Jul 26, 2018. No file in the repository changed in the last 90 days. Every commit is scored for change risk from its size, spread and the history of the files it touches.
