Tomoki Arita

Hi, I have the same problem with Xavier NX. Our result is written below Without tensorRT： ``` SuperPoint: 62.0ms NetVLAD: 15.5ms SuperGlue: 83.1ms ``` With tensorRT_fp16： ``` SuperPoint: 33.9ms NetVLAD:...

@xuhao1 @Peize-Liu

This problem has been solved. The folder for the provided CNN models contains engine caches such as TensorrtExecutionProvider_TRTKernel_graph_tf2onnx_406512749031481965_1_0_fp16_int8, but these cache files contain data that is strictly dependent on the...

Thank you! It looks like swarm_gcs receives ROS topics directly and visualizes them. Am I correct in my understanding that you are not using lcm for visualization in your project...