mAP
mAP copied to clipboard
mean Average Precision - This code evaluates the performance of your neural net for object recognition.
In the README.md introduction: >Finally, we compute the AP as the **area under this curve** (shown in light blue) by numerical integration. No approximation is involved since the curve is...
Hi, I got a test set of 121 images. When I run your script I get :  But when I calculate my AP and mAP with the `./darknet detector...
I succesfully run the code and get the correct result. But it can only set the MINOVERLAP = 0.5 or other constant value. Now Map 0.5:0.95 is a very useful...
When the animation is displayed with very big images (higher resolution than the screen) only a fraction of the image is shown. I would suggest resizeing the image before it...
Calculating AP for each class given the PR (Precision Recall) curve.  Calculating the mAP: 
训练yolov3,我的map有84%,为什么我的预测结果是这样呢 
change dir images to images-optional on conver_gt_yolo.py
Hi @Cartucho will it also be possible to generate confusion matrix beside mAP when both ground truth and prediction value are obtained?
Hi, is there any option for evaluating the segmentation results with this code?