performance of the tensorrt model on Waymo

[forwchen]

Hello, I am trying to evaluate the performance of the provided tensorrt model on waymo validation set, but not getting reasonable numbers. The data I used is from the preprocessed version of https://github.com/tianweiy/CenterPoint, which is also *.bin format.
I wonder if the provided model is only for evaluating the running time but not the mAP?

[HaohaoNJU]

the model is ready for inference, maybe you should read and print the points to checkout if the bin files are valid?