# Detection model evaluation
###### tags: `cv_infra`
## Object detection
### Training
強烈覺得要Visualize
Visualize工具：
1. wandb
2. tensorboard
3. visdom
研發雲只有tensorboard，但tensorboard好像不能顯示真實圖檔？只能有數字圖？
wandb範例

每個epoch
train/val

- obj_loss
- class_loss
- giou_loss
- outputs image
- map們
- pixel accuracy (segmentation)

https://github.com/ultralytics/yolov5/blob/master/tutorial.ipynb
https://www.jeremyjordan.me/evaluating-image-segmentation-models/ (segmentation)
https://towardsdatascience.com/metrics-to-evaluate-your-semantic-segmentation-model-6bcb99639aa2
(segmentation)
### Testing

 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.479  # <--- prune mAP
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.673
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.525
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.326
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.531
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.623
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.368
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.603
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.652. # <--- prune mAR
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.490
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.705
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.793


https://github.com/ultralytics/yolov5
https://github.com/ultralytics/yolov5/issues/304