ultralytics/yolov3: v8 - Final Darknet Compatible Release
Bibliographic record
Abstract
This is the final release of the darknet-compatible version of the https://github.com/ultralytics/yolov3 repository. This release is backwards-compatible with darknet *.cfg files for model configuration. All pytorch (<em>.pt) and darknet (</em>.weights) models/backbones available are attached to this release in the Assets section below. Breaking Changes There are no breaking changes in this release. Bug Fixes Various Added Functionality Various Speed https://cloud.google.com/deep-learning-vm/<br> <strong>Machine type:</strong> preemptible n1-standard-8 (8 vCPUs, 30 GB memory)<br> <strong>CPU platform:</strong> Intel Skylake<br> <strong>GPUs:</strong> K80 ($0.14/hr), T4 ($0.11/hr), V100 ($0.74/hr) CUDA with Nvidia Apex FP16/32<br> <strong>HDD:</strong> 300 GB SSD <strong>Dataset:</strong> COCO train 2014 (117,263 images)<br> <strong>Model:</strong> <code>yolov3-spp.cfg</code><br> <strong>Command:</strong> <code>python3 train.py --data coco2017.data --img 416 --batch 32</code> GPU n <code>--batch-size</code> img/s epoch<br>time epoch<br>cost K80 1 32 x 2 11 175 min $0.41 T4 1<br>2 32 x 2<br>64 x 1 41<br>61 48 min<br>32 min $0.09<br>$0.11 V100 1<br>2 32 x 2<br>64 x 1 122<br><strong>178</strong> 16 min<br><strong>11 min</strong> <strong>$0.21</strong><br>$0.28 2080Ti 1<br>2 32 x 2<br>64 x 1 81<br>140 24 min<br>14 min -<br>- mAP <i></i> Size COCO mAP<br>@0.5...0.95 COCO mAP<br>@0.5 YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br><strong>YOLOv3-SPP-ultralytics</strong> 320 14.0<br>28.7<br>30.5<br><strong>37.7</strong> 29.1<br>51.8<br>52.3<br><strong>56.8</strong> YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br><strong>YOLOv3-SPP-ultralytics</strong> 416 16.0<br>31.2<br>33.9<br><strong>41.2</strong> 33.0<br>55.4<br>56.9<br><strong>60.6</strong> YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br><strong>YOLOv3-SPP-ultralytics</strong> 512 16.6<br>32.7<br>35.6<br><strong>42.6</strong> 34.9<br>57.7<br>59.5<br><strong>62.4</strong> YOLOv3-tiny<br>YOLOv3<br>YOLOv3-SPP<br><strong>YOLOv3-SPP-ultralytics</strong> 608 16.6<br>33.1<br>37.0<br><strong>43.1</strong> 35.4<br>58.2<br>60.7<br><strong>62.8</strong> TODO NA
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.003 | 0.000 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.025 | 0.047 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".