search

pjreddie / darknet

Convolutional Neural Networks
http://pjreddie.com/darknet/
Other
25.77k stars 21.33k forks source link

Calculate mAP is so slow #2405

Open Steven-Wang11 opened 3 years ago

Steven-Wang11 commented 3 years ago

I train my YOLOv4 on colab. Training and Testing is working fine, except using map to calculate mAP. This is my command ! cd darknet; ./darknet detector map /content/tumor/cfg/tumor.data /content/tumor/cfg/tumor.cfg /content/tumor/weights/tumor_best.weights > result.txt

I want to check my best.weights mAP or TP, FP, F1-Score, but I get this output. The number in the last line is increasing. Looks endless

yolo] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.05
Total BFLOPS 59.563 
avg_outputs = 489778 
Loading weights from /content/tumor/weights/tumor_best.weights...Done! Loaded 162 layers from weights-file 
60
dhruvmsheth commented 3 years ago

I get mAP of around 53.1

ahmad-omran commented 9 months ago

I train my YOLOv4 on colab. Training and Testing is working fine, except using map to calculate mAP. This is my command ! cd darknet; ./darknet detector map /content/tumor/cfg/tumor.data /content/tumor/cfg/tumor.cfg /content/tumor/weights/tumor_best.weights > result.txt

I want to check my best.weights mAP or TP, FP, F1-Score, but I get this output. The number in the last line is increasing. Looks endless

yolo] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.05
Total BFLOPS 59.563 
avg_outputs = 489778 
Loading weights from /content/tumor/weights/tumor_best.weights...Done! Loaded 162 layers from weights-file 
60

Hello... Did you find the reason for this problem?