bird-feeder/BirdFSD-YOLOv5: BirdFSD-YOLOv5-v1.0.0-alpha.4

Training start time: 2022-05-06T05:38:22 Training duration: 19:59:24 W&B run URL: https://wandb.ai/biodiv/train/runs/808p95Vj W&B run ID: 808p95Vj W&B run name: peach-wave-60 W&B run path: biodiv/train/808p95Vj Number of classes: 14 Dataset name: dataset-YOLO-05-06-2022_02.57.11.tar

<details> <summary>System hardware</summary> <table> <tr> <td>CPU count <td>GPU count <td>GPU type <td>NVIDIA driver version <tr> <td>40 <td>1 <td>Tesla V100-PCIE-32GB <td>470.103.01 </table> </details><details> <summary>Base ML framework</summary> <table> <tr> <td>Python <td>CUDA <td>Torch <td>Torchvision <tr> <td>3.8.13 <td>10.2 <td>1.11.0 <td>0.12.0 </table> </details> <details> <summary>Classes</summary> ```JSON { "American Goldfinch": 118, "Brown-headed Cowbird": 186, "Carolina Chickadee": 324, "Chipping Sparrow": 1084, "Downy Woodpecker": 114, "Hermit Thrush": 141, "House Finch": 566, "Northern Cardinal": 547, "Song Sparrow": 53, "Spotted/Eastern Towhee (Rufous-sided Towhee)": 110, "Tufted Titmouse": 418, "White-throated Sparrow": 32, "Yellow-rumped Warbler": 404, "squirrels": 248 } ``` <img src="https://s3.aibird.me/public/hist.jpg" alt="classes-hist"> </details><details> <summary>Validation predictions</summary> <img src="https://s3.aibird.me/public/Validation_300_26849841f3ccb464e248.jpg" alt="val-0"> <img src="https://s3.aibird.me/public/Validation_300_4636a60a898286200daf.jpg" alt="val-1"> <img src="https://s3.aibird.me/public/Validation_300_5e0f9f3b998c3b664ad7.jpg" alt="val-2"> <img src="https://s3.aibird.me/public/Validation_300_7e96485d58cc50897f85.jpg" alt="val-3"> <img src="https://s3.aibird.me/public/Validation_300_999c06c1ec14702d4471.jpg" alt="val-4"> <img src="https://s3.aibird.me/public/Validation_300_b1f4bf8085da7835f6a6.jpg" alt="val-5"> </details><details> <summary>Confusion matrix</summary> <img src="https://s3.aibird.me/public/Results_300_0756888e6c57985e1fb1.png" alt="cm" width="1280" height="720"> </details>

Model performance:

<table> <tr> <td>best/precision <td>best/recall <td>val/box_loss <td>val/cls_loss <td>val/obj_loss <td>F1-score<tr> <td>0.9509 <td>0.9908 <td>0.0142 <td>0.0007 <td>0.0067 <td>0.9704</table>