Open tkbchan opened 2 years ago
please install pycocotools and put coco style gt file as https://github.com/WongKinYiu/ScaledYOLOv4/blob/yolov4-large/test.py#L228
If I install pycocotools with this
!pip install pycocotools-windows
Then what should I do next? I'm using google colab
This is what happened when I used test.py
I still didn't get this
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.51244
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.69771
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.56180
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.35021
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.56247
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.63983
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.38530
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.64048
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.69801
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.55487
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.74368
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.82826
set opt.save_json = True https://github.com/WongKinYiu/ScaledYOLOv4/blob/yolov4-large/test.py#L264
I got a JSON file. What should I do with it?
I'm still not getting this
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.51244
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.69771
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.56180
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.35021
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.56247
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.63983
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.38530
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.64048
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.69801
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.55487
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.74368
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.82826
hey @WongKinYiu thank you for your great work I have followed your directions and i am getting coco style results byt the AP values are way less than the ones without --save-json command.
i am getting APs , APm, APl in decimals like 0.0001 which is not right.
Can you please guide
my mAP is 0.66 without save-json= true. I need coco format results for my APs(average precision small)
I'm using this Scaled YOLOv4 to train a customized model. I followed the command for test.py but all I got was P, R, mAP .5 and .95.
In the readMe file of your repository, I saw that your test.py showed this:
which I don't get when I use the test.py. All I get is