Getting Started

The dataset configs are located within tools/cfgs/dataset_configs, and the model configs are located within tools/cfgs for different datasets.

Dataset Preparation

Currently we provide the dataloader of KITTI, NuScenes, Waymo, Lyft and Pandaset. If you want to use a custom dataset, Please refer to our custom dataset template.

KITTI Dataset

Please download the official KITTI 3D object detection dataset and organize the downloaded files as follows (the road planes could be downloaded from [road plane], which are optional for data augmentation in the training):
If you would like to train CaDDN, download the precomputed depth maps for the KITTI training set
NOTE: if you already have the data infos from pcdet v0.1, you can choose to use the old infos and set the DATABASE_WITH_FAKELIDAR option in tools/cfgs/dataset_configs/kitti_dataset.yaml as True. The second choice is that you can create the infos and gt database again and leave the config unchanged.

OpenPCDet
├── data
│   ├── kitti
│   │   │── ImageSets
│   │   │── training
│   │   │   ├──calib & velodyne & label_2 & image_2 & (optional: planes) & (optional: depth_2)
│   │   │── testing
│   │   │   ├──calib & velodyne & image_2
├── pcdet
├── tools

Generate the data infos by running the following command:

python -m pcdet.datasets.kitti.kitti_dataset create_kitti_infos tools/cfgs/dataset_configs/kitti_dataset.yaml

NuScenes Dataset

Please download the official NuScenes 3D object detection dataset and organize the downloaded files as follows:

OpenPCDet
├── data
│   ├── nuscenes
│   │   │── v1.0-trainval (or v1.0-mini if you use mini)
│   │   │   │── samples
│   │   │   │── sweeps
│   │   │   │── maps
│   │   │   │── v1.0-trainval  
├── pcdet
├── tools

Install the nuscenes-devkit with version 1.0.5 by running the following command:

pip install nuscenes-devkit==1.0.5

Generate the data infos by running the following command (it may take several hours):

# for lidar-only setting
python -m pcdet.datasets.nuscenes.nuscenes_dataset --func create_nuscenes_infos \
    --cfg_file tools/cfgs/dataset_configs/nuscenes_dataset.yaml \
    --version v1.0-trainval

# for multi-modal setting
python -m pcdet.datasets.nuscenes.nuscenes_dataset --func create_nuscenes_infos \
    --cfg_file tools/cfgs/dataset_configs/nuscenes_dataset.yaml \
    --version v1.0-trainval \
    --with_cam

Waymo Open Dataset

Please download the official Waymo Open Dataset, including the training data training_0000.tar~training_0031.tar and the validation data validation_0000.tar~validation_0007.tar.
Unzip all the above xxxx.tar files to the directory of data/waymo/raw_data as follows (You could get 798 train tfrecord and 202 val tfrecord ):

OpenPCDet
├── data
│   ├── waymo
│   │   │── ImageSets
│   │   │── raw_data
│   │   │   │── segment-xxxxxxxx.tfrecord
|   |   |   |── ...
|   |   |── waymo_processed_data_v0_5_0
│   │   │   │── segment-xxxxxxxx/
|   |   |   |── ...
│   │   │── waymo_processed_data_v0_5_0_gt_database_train_sampled_1/  (old, for single-frame)
│   │   │── waymo_processed_data_v0_5_0_waymo_dbinfos_train_sampled_1.pkl  (old, for single-frame)
│   │   │── waymo_processed_data_v0_5_0_gt_database_train_sampled_1_global.npy (optional, old, for single-frame)
│   │   │── waymo_processed_data_v0_5_0_infos_train.pkl (optional)
│   │   │── waymo_processed_data_v0_5_0_infos_val.pkl (optional)
|   |   |── waymo_processed_data_v0_5_0_gt_database_train_sampled_1_multiframe_-4_to_0 (new, for single/multi-frame)
│   │   │── waymo_processed_data_v0_5_0_waymo_dbinfos_train_sampled_1_multiframe_-4_to_0.pkl (new, for single/multi-frame)
│   │   │── waymo_processed_data_v0_5_0_gt_database_train_sampled_1_multiframe_-4_to_0_global.np  (new, for single/multi-frame)
 
├── pcdet
├── tools

Install the official waymo-open-dataset by running the following command:

pip3 install --upgrade pip
# tf 2.0.0
pip3 install waymo-open-dataset-tf-2-5-0 --user

Extract point cloud data from tfrecord and generate data infos by running the following command (it takes several hours, and you could refer to data/waymo/waymo_processed_data_v0_5_0 to see how many records that have been processed):

# only for single-frame setting
python -m pcdet.datasets.waymo.waymo_dataset --func create_waymo_infos \
    --cfg_file tools/cfgs/dataset_configs/waymo_dataset.yaml

# for single-frame or multi-frame setting
python -m pcdet.datasets.waymo.waymo_dataset --func create_waymo_infos \
    --cfg_file tools/cfgs/dataset_configs/waymo_dataset_multiframe.yaml
# Ignore 'CUDA_ERROR_NO_DEVICE' error as this process does not require GPU.

Note that you do not need to install waymo-open-dataset if you have already processed the data before and do not need to evaluate with official Waymo Metrics.

Argoverse2 Dataset

Download the Argoverse 2 Sensor Dataset from the official website, and then extract them.
Install the official API of Argoverse 2

pip install av2==0.2.0

Generate info files for train and val.

python -m pcdet.datasets.argo2.argo2_dataset --root_path data/argo2/sensor --output_dir data/argo2

Note that this issue from the argo2 api might be noticed.
If the CPU memory of your machine is limited, you can set --workers=0 in the training script.
The organized files are as follows:

OpenPCDet
├── data
│   ├── argo2
│   │   │── ImageSets
│   │   │   ├──train.txt & val.txt
│   │   │── training
│   │   │   ├──velodyne
│   │   │── sensor
│   │   │   ├──val
│   │   │── argo2_infos_train.pkl
│   │   │── argo2_infos_val.pkl
│   │   │── val_anno.feather

├── pcdet
├── tools

ONCE Dataset

Please download train/val/test of the official ONCE Dataset and organize the downloaded files as follows:
Note that the whole dataset is large (2TB) and most scenes are unlabeled, so if you only need ONCE for supervised 3D object detection and model development, you can just download the training/validation/testing split. If you use ONCE for semi-supervised/self-supervised 3D object detection, you can choose to download the respective unlabeled splits (unlabeled small split: 100k unlabeled scenes; unlabeled medium split: 500k unlabeled scenes; unlabeled large split: 1M unlabeled scenes).

ONCE_Benchmark
├── data
│   ├── once
│   │   │── ImageSets
|   |   |   ├──train.txt
|   |   |   ├──val.txt
|   |   |   ├──test.txt
|   |   |   ├──raw_small.txt (100k unlabeled)
|   |   |   ├──raw_medium.txt (500k unlabeled)
|   |   |   ├──raw_large.txt (1M unlabeled)
│   │   │── data
│   │   │   ├──000000
|   |   |   |   |──000000.json (infos)
|   |   |   |   |──lidar_roof (point clouds)
|   |   |   |   |   |──frame_timestamp_1.bin
|   |   |   |   |  ...
|   |   |   |   |──cam0[1-9] (images)
|   |   |   |   |   |──frame_timestamp_1.jpg
|   |   |   |   |  ...
|   |   |   |  ...
├── pcdet
├── tools

Generate the data infos by running the following command:

python -m pcdet.datasets.once.once_dataset --func create_once_infos --cfg_file tools/cfgs/dataset_configs/once_dataset.yaml

Lyft Dataset

Please download the official Lyft Level5 perception dataset and organize the downloaded files as follows:

OpenPCDet
├── data
│   ├── lyft
│   │   │── ImageSets
│   │   │── trainval
│   │   │   │── data & maps(train_maps) & images(train_images) & lidar(train_lidar) & train_lidar
│   │   │── test
│   │   │   │── data & maps(test_maps) & test_images & test_lidar
├── pcdet
├── tools

Install the lyft-dataset-sdk with version 0.0.8 by running the following command:

pip install -U lyft_dataset_sdk==0.0.8

Generate the training & validation data infos by running the following command (it may take several hours):

python -m pcdet.datasets.lyft.lyft_dataset --func create_lyft_infos \
    --cfg_file tools/cfgs/dataset_configs/lyft_dataset.yaml

Generate the test data infos by running the following command:

python -m pcdet.datasets.lyft.lyft_dataset --func create_lyft_infos \
    --cfg_file tools/cfgs/dataset_configs/lyft_dataset.yaml --version test

You need to check carefully since we don't provide a benchmark for it.

Pretrained Models

If you would like to train CaDDN, download the pretrained DeepLabV3 model and place within the checkpoints directory. Please make sure the kornia is installed since it is needed for CaDDN.

OpenPCDet
├── checkpoints
│   ├── deeplabv3_resnet101_coco-586e9e4e.pth
├── data
├── pcdet
├── tools

Training & Testing

Test and evaluate the pretrained models

Test with a pretrained model:

python test.py --cfg_file ${CONFIG_FILE} --batch_size ${BATCH_SIZE} --ckpt ${CKPT}

To test all the saved checkpoints of a specific training setting and draw the performance curve on the Tensorboard, add the --eval_all argument:

python test.py --cfg_file ${CONFIG_FILE} --batch_size ${BATCH_SIZE} --eval_all

To test with multiple GPUs:

sh scripts/dist_test.sh ${NUM_GPUS} \
    --cfg_file ${CONFIG_FILE} --batch_size ${BATCH_SIZE}

# or

sh scripts/slurm_test_mgpu.sh ${PARTITION} ${NUM_GPUS} \
    --cfg_file ${CONFIG_FILE} --batch_size ${BATCH_SIZE}

Train a model

You could optionally add extra command line parameters --batch_size ${BATCH_SIZE} and --epochs ${EPOCHS} to specify your preferred parameters.

Train with multiple GPUs or multiple machines

sh scripts/dist_train.sh ${NUM_GPUS} --cfg_file ${CONFIG_FILE}

# or 

sh scripts/slurm_train.sh ${PARTITION} ${JOB_NAME} ${NUM_GPUS} --cfg_file ${CONFIG_FILE}

Train with a single GPU:

python train.py --cfg_file ${CONFIG_FILE}

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!