佛山最好的网站建设,只用php做网站,起飞页自助建站平台的特点,品牌建设规划制定及实施情况博主在进行DINO-DETR模型实验时#xff0c;使用缩减后的COCO数据集进行训练#xff0c;发现其mAP值只能达到0.27作用#xff0c;故而修改了下pycocotool的代码#xff0c;令其输出每个类别的AP值#xff0c;来看看是由于什么原因导致这个问题。 之所以这样是因为博主认为各…博主在进行DINO-DETR模型实验时使用缩减后的COCO数据集进行训练发现其mAP值只能达到0.27作用故而修改了下pycocotool的代码令其输出每个类别的AP值来看看是由于什么原因导致这个问题。 之所以这样是因为博主认为各类别的AP值是不均匀的必定由学得好的与学得不好的。 参数设置batch-size1,lr0.00005 使用22个epoch中训练结果最好的那个进行验证结果如下
【truckcarbus】分别为0.020.110.70map为0.28
batch-size2,lr0.0001,epoch24。结果如下 随后使用官方给定的训练后的模型进行测试
【person, bicycle, car, motorcycle, airplane, bus, train, truck】对应carbustruck为0.490.720.42map值为0.54
上述实验结果首先证明了博主的猜想即各个类别的AP值是不同的也就说明其并非是对所有类别信息都有一个较好的结果。 其次尝试分析一下造成这个问题的原因。 首先在我们缩小的COCO数据集上尽管car的标注较多但目标都较小而且存在很大程度的遮挡。且car在出现时背景复杂多变有时是通过窗户看到有时出现在马路上有时旁边出现其他的物体周边出现多种信息。 而bus尽管数量上并不占优但其在出现时特征较为明显显示较为完整且出现时背景较为固定。多为公路上出现故而其学习效果较好。 博主选择了几个具有代表性的图像进行展示用以证实博主上面的猜想。 使用DINO-DETR官方给定的权重模型来验证完整COCO数据集完整结果如下
IoU metric: bboxAverage Precision (AP) [ IoU0.50:0.95 | area all | maxDets100 ] 0.491, per category [ 0.607 0.368 0.493 0.505 0.750 0.727 0.723 0.428 0.321 0.3130.709 0.690 0.530 0.293 0.434 0.793 0.721 0.654 0.603 0.6380.717 0.781 0.752 0.730 0.192 0.468 0.216 0.421 0.528 0.7290.301 0.457 0.518 0.509 0.388 0.423 0.576 0.461 0.568 0.4340.442 0.495 0.464 0.280 0.264 0.471 0.310 0.270 0.431 0.3920.262 0.277 0.481 0.610 0.560 0.447 0.345 0.499 0.306 0.5190.336 0.664 0.637 0.676 0.651 0.401 0.579 0.416 0.638 0.3980.566 0.424 0.671 0.200 0.568 0.418 0.356 0.540 0.169 0.349]Average Precision (AP) [ IoU0.50 | area all | maxDets100 ] 0.667, per category [ 0.854 0.625 0.734 0.775 0.898 0.854 0.879 0.590 0.578 0.5790.869 0.777 0.706 0.406 0.639 0.921 0.852 0.856 0.832 0.8480.898 0.910 0.925 0.899 0.339 0.683 0.363 0.644 0.740 0.9090.574 0.618 0.746 0.735 0.630 0.707 0.791 0.698 0.822 0.6230.654 0.657 0.637 0.442 0.377 0.609 0.466 0.378 0.566 0.5120.446 0.417 0.639 0.797 0.714 0.650 0.529 0.634 0.498 0.6580.469 0.794 0.813 0.806 0.831 0.597 0.737 0.622 0.767 0.5520.713 0.644 0.780 0.380 0.781 0.591 0.479 0.698 0.216 0.496]Average Precision (AP) [ IoU0.75 | area all | maxDets100 ] 0.536, per category [ 0.660 0.353 0.531 0.537 0.822 0.799 0.812 0.481 0.303 0.3120.802 0.742 0.564 0.315 0.447 0.836 0.778 0.730 0.664 0.7060.790 0.833 0.841 0.791 0.199 0.510 0.219 0.462 0.585 0.8600.268 0.515 0.592 0.572 0.416 0.461 0.621 0.500 0.626 0.4880.465 0.547 0.500 0.291 0.291 0.525 0.333 0.298 0.476 0.4260.268 0.302 0.501 0.680 0.615 0.497 0.365 0.536 0.341 0.5270.351 0.729 0.715 0.741 0.775 0.480 0.635 0.446 0.738 0.4120.713 0.417 0.746 0.187 0.634 0.437 0.363 0.579 0.200 0.428]Average Precision (AP) [ IoU0.50:0.95 | area small | maxDets100 ] 0.327, per category [ 0.409 0.223 0.388 0.338 0.704 0.394 0.449 0.238 0.246 0.2670.448 0.346 0.263 0.184 0.315 0.396 0.494 0.351 0.438 0.5310.516 0.681 0.612 0.457 0.206 0.302 0.185 0.324 0.383 0.6660.292 0.332 0.482 0.519 0.410 0.382 0.461 0.315 0.478 0.3260.279 0.333 0.301 0.204 0.244 0.263 0.159 0.095 0.121 0.2270.154 0.204 0.314 0.385 0.423 0.324 0.255 0.131 0.195 0.0290.055 0.069 0.332 0.194 0.546 0.349 0.284 0.288 0.250 0.1130.532 0.296 0.800 0.164 0.459 0.275 0.115 0.176 0.131 0.309]Average Precision (AP) [ IoU0.50:0.95 | areamedium | maxDets100 ] 0.524, per category [ 0.675 0.427 0.637 0.456 0.735 0.578 0.348 0.455 0.370 0.5120.722 0.729 0.459 0.263 0.619 0.763 0.726 0.645 0.647 0.6750.661 0.781 0.722 0.770 0.189 0.514 0.288 0.554 0.510 0.8170.416 0.688 0.806 0.556 0.465 0.503 0.693 0.537 0.638 0.5880.589 0.620 0.629 0.456 0.354 0.517 0.333 0.441 0.276 0.4330.303 0.359 0.599 0.511 0.614 0.505 0.387 0.382 0.372 0.1970.199 0.573 0.608 0.573 0.752 0.561 0.583 0.545 0.614 0.3250.538 0.484 0.415 0.292 0.678 0.490 0.465 0.496 0.279 0.403]Average Precision (AP) [ IoU0.50:0.95 | area large | maxDets100 ] 0.630, per category [ 0.796 0.650 0.734 0.659 0.784 0.864 0.767 0.572 0.507 0.6130.856 0.961 0.780 0.492 0.817 0.813 0.760 0.809 0.720 0.7790.789 0.810 0.849 0.778 0.274 0.621 0.155 0.701 0.742 0.8940.221 0.541 0.686 0.421 0.027 0.583 0.548 0.664 0.575 0.6970.789 0.729 0.594 0.423 0.440 0.639 0.543 0.438 0.576 0.6010.285 0.342 0.603 0.732 0.817 0.539 0.484 0.563 0.324 0.5540.470 0.734 0.748 0.807 0.802 0.634 0.684 0.692 0.783 0.4900.824 0.485 0.740 0.401 0.619 0.650 0.535 0.704 0.482 0.830]Average Recall (AR) [ IoU0.50:0.95 | area all | maxDets 1 ] 0.379, per category [ 0.205 0.289 0.192 0.299 0.583 0.562 0.668 0.396 0.158 0.1460.680 0.719 0.427 0.290 0.215 0.769 0.664 0.400 0.141 0.1920.294 0.589 0.279 0.386 0.253 0.283 0.252 0.348 0.231 0.6150.243 0.446 0.450 0.196 0.387 0.388 0.527 0.360 0.502 0.2540.208 0.314 0.441 0.276 0.292 0.352 0.148 0.159 0.382 0.1740.110 0.111 0.262 0.429 0.149 0.273 0.188 0.522 0.271 0.5960.425 0.604 0.555 0.614 0.609 0.310 0.515 0.443 0.704 0.4440.722 0.440 0.606 0.090 0.483 0.310 0.450 0.382 0.409 0.304]Average Recall (AR) [ IoU0.50:0.95 | area all | maxDets 10 ] 0.651, per category [ 0.613 0.509 0.588 0.606 0.830 0.811 0.832 0.705 0.454 0.4590.819 0.816 0.725 0.508 0.445 0.902 0.861 0.738 0.608 0.6420.765 0.894 0.784 0.800 0.506 0.602 0.503 0.540 0.597 0.8130.481 0.633 0.605 0.557 0.608 0.564 0.699 0.599 0.729 0.5740.568 0.649 0.680 0.522 0.561 0.701 0.434 0.493 0.751 0.5310.417 0.435 0.634 0.725 0.577 0.577 0.512 0.789 0.577 0.7930.652 0.813 0.790 0.800 0.756 0.619 0.779 0.650 0.827 0.6650.822 0.666 0.814 0.299 0.743 0.628 0.639 0.704 0.600 0.570]Average Recall (AR) [ IoU0.50:0.95 | area all | maxDets100 ] 0.727, per category [ 0.735 0.599 0.682 0.704 0.877 0.837 0.865 0.791 0.604 0.5370.824 0.820 0.792 0.612 0.599 0.909 0.869 0.809 0.766 0.7920.871 0.904 0.865 0.857 0.590 0.718 0.587 0.597 0.721 0.8230.590 0.686 0.650 0.700 0.695 0.596 0.739 0.666 0.759 0.6820.643 0.734 0.718 0.592 0.624 0.767 0.659 0.640 0.792 0.6940.626 0.609 0.742 0.792 0.748 0.733 0.658 0.848 0.651 0.8450.718 0.857 0.803 0.832 0.759 0.682 0.783 0.672 0.827 0.7060.822 0.707 0.850 0.526 0.764 0.709 0.650 0.769 0.709 0.607]Average Recall (AR) [ IoU0.50:0.95 | area small | maxDets100 ] 0.563, per category [ 0.575 0.433 0.587 0.553 0.777 0.550 0.675 0.662 0.490 0.4910.648 0.644 0.619 0.435 0.486 0.625 0.616 0.627 0.630 0.6780.753 0.840 0.717 0.677 0.522 0.532 0.483 0.475 0.561 0.7520.510 0.542 0.612 0.648 0.609 0.531 0.597 0.524 0.644 0.5940.516 0.611 0.574 0.502 0.517 0.592 0.490 0.460 0.372 0.5200.431 0.492 0.536 0.581 0.631 0.544 0.518 0.344 0.491 0.7000.305 0.386 0.533 0.565 0.660 0.619 0.394 0.534 0.525 0.3400.900 0.502 0.800 0.449 0.666 0.565 0.362 0.428 0.600 0.556]Average Recall (AR) [ IoU0.50:0.95 | areamedium | maxDets100 ] 0.767, per category [ 0.800 0.687 0.812 0.684 0.879 0.768 0.656 0.795 0.663 0.7100.823 0.833 0.762 0.650 0.799 0.832 0.868 0.793 0.791 0.8300.821 0.846 0.838 0.831 0.686 0.750 0.728 0.757 0.747 0.9200.805 0.904 0.933 0.815 0.808 0.710 0.838 0.727 0.802 0.8050.764 0.836 0.829 0.761 0.834 0.790 0.682 0.744 0.754 0.7370.632 0.705 0.800 0.759 0.801 0.756 0.708 0.759 0.688 0.4640.598 0.768 0.786 0.734 0.845 0.853 0.782 0.809 0.824 0.6350.760 0.751 0.750 0.721 0.837 0.785 0.767 0.739 0.633 0.661]Average Recall (AR) [ IoU0.50:0.95 | area large | maxDets100 ] 0.883, per category [ 0.900 0.852 0.919 0.825 0.919 0.933 0.892 0.899 0.867 0.8680.932 0.985 0.939 0.815 0.933 0.934 0.905 0.916 0.889 0.9310.920 0.925 0.945 0.924 0.650 0.905 0.790 0.905 0.882 0.9380.975 0.780 0.757 0.814 0.800 0.633 0.900 0.879 0.958 0.9170.929 0.908 0.932 0.838 0.857 0.922 0.881 0.887 0.910 0.8940.769 0.762 0.900 0.882 0.952 0.878 0.882 0.897 0.813 0.8820.885 0.917 0.890 0.933 0.922 0.893 0.907 0.939 0.900 0.7950.900 0.848 0.879 0.832 0.864 0.916 0.843 0.914 0.967 0.900]
