pytorch-yolo-v3
pytorch-yolo-v3 copied to clipboard
What does each column mean in `prediction` ?
trafficstars
Specifically column 5 (0.9952), column 6(0.9997),which is the precision?
i know
- column 0 is index of images
- column[1-4] is the bbox
- last column is the index of coco.names
output:
$ python detect.py --images imgs/dog.jpg --det det
Loading network.....
Network successfully loaded
prediction = tensor([
[ 0.0000, 89.2452, 110.7772, 303.7112, 294.3270, 0.9952, 0.9997, 1.0000],
[ 0.0000, 256.4473, 98.3855, 373.3513, 144.1134, 0.9954, 0.9407, 7.0000],
[ 0.0000, 69.5613, 173.2573, 170.4126, 343.0031, 0.9997, 0.9894, 16.0000]])
dog.jpg predicted in 0.150 seconds
Objects Detected: bicycle truck dog
----------------------------------------------------------
SUMMARY
----------------------------------------------------------
Task : Time Taken (in seconds)
Reading addresses : 0.000
Loading batch : 0.178
Detection (1 images) : 0.150
Output Processing : 0.000
Drawing Boxes : 0.004
Average time_per_img : 0.333
----------------------------------------------------------