CP-Freezer

Dataset and Model Download

Please visit the official website of OPV2V for latest dataset and pre-trained model download instructions.

Environment Setup

We use pixi for easier and faster env setup. More information can be found at here.

We used CUDA 11.8 for testing. For different versions of CUDA (e.g., 12.0), please edit the pixi.toml file to change the pytorch-cuda version and spconv-cu118 version accordingly (e.g., spconv-cu120).

Next, with pixi installed, simply run the following command to get the package installed (if not yet) in the virtual environment and activate it (to deactivate simply run exit).

pixi shell

Finally, setup and build the dependencies for OpenCOOD, NMS GPU version using the following commands:

pixi run opencood_setup
pixi run nms_gpu_build

Evaluation

The batch evaluation script is provided in /eval_script/latency_attack.sh. Make sure the model directory and data directory in the script are pointing to the correct paths. Then, run the evaluation with the following commands, with latency attack as an example:

sudo chmod a+x latency_attack.sh
./latency_attack.sh

The results will be saved to the corresponding model directories.