Open limih0212 opened 1 year ago
I have same issue here, i use waymo dataset v1.4.2 with 10 Val tfrecord. And got result from waymo_eval like this
OBJECT_TYPE_TYPE_VEHICLE_LEVEL_2/AP [0.26191792]
OBJECT_TYPE_TYPE_VEHICLE_LEVEL_2/APH [0.25024492]
OBJECT_TYPE_TYPE_VEHICLE_LEVEL_2/Recall@0.95 [0.0]
OBJECT_TYPE_TYPE_PEDESTRIAN_LEVEL_2/AP [0.4423461]
OBJECT_TYPE_TYPE_PEDESTRIAN_LEVEL_2/APH [0.3565605]
OBJECT_TYPE_TYPE_PEDESTRIAN_LEVEL_2/Recall@0.95 [0.0]
OBJECT_TYPE_TYPE_SIGN_LEVEL_2/AP [0.0]
OBJECT_TYPE_TYPE_SIGN_LEVEL_2/APH [0.0]
OBJECT_TYPE_TYPE_SIGN_LEVEL_2/Recall@0.95 [0.0]
OBJECT_TYPE_TYPE_CYCLIST_LEVEL_2/AP [0.030788602]
OBJECT_TYPE_TYPE_CYCLIST_LEVEL_2/APH [0.028065205]
OBJECT_TYPE_TYPE_CYCLIST_LEVEL_2/Recall@0.95 [0.0]
But the result is quite good if using your bin file Please help @HaohaoNJU thank you
Looks like your pkl file xyz is like this, (very small number)
while waymo have like this
First of all, thank you for your project.
I converted waymo dataset to pkl file according to this guide. And I created a bin file with your "generate_input_data.py".
When I used these bin files, the detection result did not reach your sample result. Again, the detection results of your samples (seq_0_frame_101.bin and seq_0_frame_100.bin) were very good.
Is this an error in bin file creation? If my PC environment was a problem, the detection results of seq_0_frame_101.bin and seq_0_frame_100.bin would not be as good as the sample.
The environment in which I created the bin file is as follows. And I attach the bin file and the result that I used.
./build/centerpoint --pfeOnnxPath=models/pfe_baseline32000.onnx --rpnOnnxPath=models/rpn_baseline.onnx --savePath=results --filePath=lidars --fp16
seq_0_frame_197.bin.txt seq_0_frame_197.zip