RT-DETR详解与实战

测试结果

                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 15/15 [00:02<00:00,  5.30it/s]
                   all        230       1412      0.956      0.968      0.982      0.725
                   c17        230        131       0.97      0.978      0.991      0.815
                    c5        230         68      0.898      0.903      0.933      0.791
            helicopter        230         43      0.976      0.936      0.978      0.615
                  c130        230         85      0.973      0.976      0.981      0.675
                   f16        230         57      0.972      0.965       0.99      0.683
                    b2        230          2      0.854          1      0.995      0.749
                 other        230         86      0.975      0.893      0.963      0.535
                   b52        230         70      0.956      0.922      0.965      0.813
                  kc10        230         62      0.958      0.984      0.985      0.822
               command        230         40      0.988          1      0.995      0.805
                   f15        230        123      0.992      0.971      0.995      0.694
                 kc135        230         91      0.945      0.967      0.965       0.68
                   a10        230         27      0.957      0.817      0.922      0.356
                    b1        230         20      0.961       0.95      0.946      0.693
                   aew        230         25      0.925      0.982      0.992      0.789
                   f22        230         17       0.99          1      0.995      0.725
                    p3        230        105       0.99      0.978      0.995      0.759
                    p8        230          1       0.84          1      0.995      0.697
                   f35        230         32      0.969      0.962      0.991      0.562
                   f18        230        125      0.949      0.984      0.986      0.797
                   v22        230         41      0.988          1      0.995      0.709
                 su-27        230         31          1      0.972      0.995      0.835
                 il-38        230         27      0.995          1      0.995      0.801
                tu-134        230          1      0.843          1      0.995      0.901
                 su-33        230          2          1          1      0.995      0.672
                 an-70        230          2      0.947          1      0.995      0.787
                 tu-22        230         98          1      0.988      0.995      0.816
Speed: 0.3ms preprocess, 5.7ms inference, 0.0ms loss, 0.3ms postprocess per image

你可能感兴趣的:(DERT实战与改进手册,YOLO,人工智能)