git clone [email protected]:DerryHub/BEVFormer_tensorrt.git
cd BEVFormer_tensorrt
PROJECT_DIR=$(pwd)

cd ${PROJECT_DIR}/data
ln -s /path/to/coco coco

cd ${PROJECT_DIR}/data
ln -s /path/to/nuscenes nuscenes
ln -s /path/to/can_bus can_bus

cd ${PROJECT_DIR}
sh samples/bevformer/create_data.sh

${PROJECT_DIR}/data/.
├── can_bus
│   ├── scene-0001_meta.json
│   ├── scene-0001_ms_imu.json
│   ├── scene-0001_pose.json
│   └── ...
├── coco
│   ├── annotations
│   ├── test2017
│   ├── train2017
│   └── val2017
└── nuscenes
    ├── maps
    ├── samples
    ├── sweeps
    └── v1.0-trainval

cd ${PROJECT_DIR}
docker build -t trt85 -f docker/Dockerfile .
docker run -it --gpus all -v ${PROJECT_DIR}:/workspace/BEVFormer_tensorrt/ \
-v /path/to/can_bus:/workspace/BEVFormer_tensorrt/data/can_bus \
-v /path/to/coco:/workspace/BEVFormer_tensorrt/data/coco \
-v /path/to/nuscenes:/workspace/BEVFormer_tensorrt/data/nuscenes \
--shm-size 8G trt85 /bin/bash

# in container
cd /workspace/BEVFormer_tensorrt/TensorRT/build
cmake .. -DCMAKE_TENSORRT_PATH=/usr
make -j$(nproc)
make install
cd /workspace/BEVFormer_tensorrt/third_party/bev_mmdet3d
python setup.py build develop

pip install torch==1.12.1+cu116 torchvision==0.13.1+cu116 torchaudio==0.12.1+cu116 --extra-index-url https://download.pytorch.org/whl/cu116

git clone https://github.com/open-mmlab/mmcv.git
cd mmcv
git checkout v1.5.0
pip install -r requirements/optional.txt
MMCV_WITH_OPS=1 pip install -e .

git clone https://github.com/open-mmlab/mmdetection.git
cd mmdetection
git checkout v2.25.1
pip install -v -e .
# "-v" means verbose, or more output
# "-e" means installing a project in editable mode,
# thus any local modifications made to the code will take effect without reinstallation.

git clone [email protected]:open-mmlab/mmdeploy.git
cd mmdeploy
git checkout v0.10.0

git clone [email protected]:NVIDIA/cub.git third_party/cub
cd third_party/cub
git checkout c3cceac115

# go back to third_party directory and git clone pybind11
cd ..
git clone [email protected]:pybind/pybind11.git pybind11
cd pybind11
git checkout 70a58c5

export MMDEPLOY_DIR=/the/root/path/of/MMDeploy
export TENSORRT_DIR=/the/path/of/tensorrt
export CUDNN_DIR=/the/path/of/cuda

export LD_LIBRARY_PATH=$TENSORRT_DIR/lib:$LD_LIBRARY_PATH
export LD_LIBRARY_PATH=$CUDNN_DIR/lib64:$LD_LIBRARY_PATH

cd ${MMDEPLOY_DIR}
mkdir -p build
cd build
cmake -DCMAKE_CXX_COMPILER=g++-7 -DMMDEPLOY_TARGET_BACKENDS=trt -DTENSORRT_DIR=${TENSORRT_DIR} -DCUDNN_DIR=${CUDNN_DIR} ..
make -j$(nproc) 
make install

cd ${MMDEPLOY_DIR}
pip install -v -e .
# "-v" means verbose, or more output
# "-e" means installing a project in editable mode,
# thus any local modifications made to the code will take effect without reinstallation.

cd ${PROJECT_DIR}
pip install -r requirements.txt

cd ${PROJECT_DIR}/TensorRT/build
cmake .. -DCMAKE_TENSORRT_PATH=/path/to/TensorRT
make -j$(nproc)
make install

cd ${PROJECT_DIR}
sh samples/test_trt_ops.sh

cd ${PROJECT_DIR}/third_party/bev_mmdet3d
python setup.py build develop

cd ${PROJECT_DIR}
# defult gpu_id is 0
sh samples/bevformer/base/pth_evaluate.sh -d ${gpu_id}

# convert .pth to .onnx
sh samples/bevformer/base/pth2onnx.sh -d ${gpu_id}
# convert .onnx to TensorRT engine (FP32)
sh samples/bevformer/base/onnx2trt.sh -d ${gpu_id}
# convert .onnx to TensorRT engine (FP16)
sh samples/bevformer/base/onnx2trt_fp16.sh -d ${gpu_id}
# evaluate with TensorRT engine (FP32)
sh samples/bevformer/base/trt_evaluate.sh -d ${gpu_id}
# evaluate with TensorRT engine (FP16)
sh samples/bevformer/base/trt_evaluate_fp16.sh -d ${gpu_id}

# Quantization
# calibration and convert .onnx to TensorRT engine (FP32/INT8)
sh samples/bevformer/base/onnx2trt_int8.sh -d ${gpu_id}
# calibration and convert .onnx to TensorRT engine (FP16/INT8)
sh samples/bevformer/base/onnx2trt_int8_fp16.sh -d ${gpu_id}
# evaluate with TensorRT engine (FP32/INT8)
sh samples/bevformer/base/trt_evaluate_int8.sh -d ${gpu_id}
# evaluate with TensorRT engine (FP16/INT8)
sh samples/bevformer/base/trt_evaluate_int8_fp16.sh -d ${gpu_id}

# quantization aware train
# defult gpu_ids is 0,1,2,3,4,5,6,7
sh samples/bevformer/base/quant_aware_train.sh -d ${gpu_ids}
# then following the post training quantization process

# nv_half
# convert .pth to .onnx
sh samples/bevformer/plugin/base/pth2onnx.sh -d ${gpu_id}
# convert .onnx to TensorRT engine (FP32)
sh samples/bevformer/plugin/base/onnx2trt.sh -d ${gpu_id}
# convert .onnx to TensorRT engine (FP16-nv_half)
sh samples/bevformer/plugin/base/onnx2trt_fp16.sh -d ${gpu_id}
# evaluate with TensorRT engine (FP32)
sh samples/bevformer/plugin/base/trt_evaluate.sh -d ${gpu_id}
# evaluate with TensorRT engine (FP16-nv_half)
sh samples/bevformer/plugin/base/trt_evaluate_fp16.sh -d ${gpu_id}

# nv_half2
# convert .pth to .onnx
sh samples/bevformer/plugin/base/pth2onnx_2.sh -d ${gpu_id}
# convert .onnx to TensorRT engine (FP16-nv_half2)
sh samples/bevformer/plugin/base/onnx2trt_fp16_2.sh -d ${gpu_id}
# evaluate with TensorRT engine (FP16-nv_half2)
sh samples/bevformer/plugin/base/trt_evaluate_fp16_2.sh -d ${gpu_id}

# Quantization
# nv_half
# calibration and convert .onnx to TensorRT engine (FP32/INT8)
sh samples/bevformer/plugin/base/onnx2trt_int8.sh -d ${gpu_id}
# calibration and convert .onnx to TensorRT engine (FP16-nv_half/INT8)
sh samples/bevformer/plugin/base/onnx2trt_int8_fp16.sh -d ${gpu_id}
# evaluate with TensorRT engine (FP32/INT8)
sh samples/bevformer/plugin/base/trt_evaluate_int8.sh -d ${gpu_id}
# evaluate with TensorRT engine (FP16-nv_half/INT8)
sh samples/bevformer/plugin/base/trt_evaluate_int8_fp16.sh -d ${gpu_id}

# nv_half2
# calibration and convert .onnx to TensorRT engine (FP16-nv_half2/INT8)
sh samples/bevformer/plugin/base/onnx2trt_int8_fp16_2.sh -d ${gpu_id}
# evaluate with TensorRT engine (FP16-nv_half2/INT8)
sh samples/bevformer/plugin/base/trt_evaluate_int8_fp16_2.sh -d ${gpu_id}