I successfully test rectangle-graspnet-multiObject-multiGrasp, how could I get the ap evaluation result on your paper

[cww97]

scene_0189+0254.png                                                                                      │
Detection took 0.084s                                                                                    │
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~                                                                      │
scene_0189+0255.png                                                                                      │
Detection took 0.086s                                                                                    │
========================================================================                                 │
                                                                                                         │
Miss Rate: [0.62971788 0.9795459  0.99943616 0.99999805 1.        ]                                      │
FPPI: [1.87301649e+01 2.96397569e-01 3.90625000e-03 0.00000000e+00                                       │
 0.00000000e+00] 

table 3, line 2 Chu et al.[7]

[Fang-Haoshu]

Hi, you can refer to https://github.com/graspnet/graspnet-baseline. In short, you need to transform the pose into 6D representation and use the graspnet_eval function.