MOBILEPHONE DETECTOR (YOLOV4)

On this website you can try the model with your own images and buy it if you are satisfied with its accuracy. 



 

Model description:

This model detects mobilephones.

 

Number of classes: 1 (mobilephone)

 

Metrics:

detections_count = 2917, unique_truth_count = 1076
class_id = 0, name = Mobilephone, ap = 92.95%            (TP = 992, FP = 142)

for conf_thresh = 0.25, precision = 0.87, recall = 0.92, F1-score = 0.90
for conf_thresh = 0.25, TP = 992, FP = 142, FN = 84, average IoU = 76.44 %

IoU threshold = 50 %, used Area-Under-Curve for each unique Recall
mean average precision (mAP@0.50) = 0.929500, or 92.95 %

System requirements:

Inference time using CPU: 300 ms (on HP Laptop 15-DA0042NH (Processor: Intel(R) Core(TM) i7-8550U CPU))