Test and Train on Standard Datasets

Test existing models on standard datasets

  • single GPU

  • CPU

  • single node multiple GPU

  • multiple node

You can use the following commands to test a dataset.

# single-gpu testing
python tools/ ${CONFIG_FILE} ${CHECKPOINT_FILE} [--cfg-options test_evaluator.pklfile_prefix=${RESULT_FILE}]  [--show] [--show-dir ${SHOW_DIR}]

# CPU: disable GPUs and run single-gpu testing script (experimental)
python tools/ ${CONFIG_FILE} ${CHECKPOINT_FILE} [--cfg-options test_evaluator.pklfile_prefix=${RESULT_FILE}]  [--show] [--show-dir ${SHOW_DIR}]

# multi-gpu testing
./tools/ ${CONFIG_FILE} ${CHECKPOINT_FILE} ${GPU_NUM} [--cfg-options test_evaluator.pklfile_prefix=${RESULT_FILE}]  [--show] [--show-dir ${SHOW_DIR}]


For now, CPU testing is only supported for SMOKE.

Optional arguments:

  • --show: If specified, detection results will be plotted in the silient mode. It is only applicable to single GPU testing and used for debugging and visualization. This should be used with --show-dir.

  • --show-dir: If specified, detection results will be plotted on the ***_points.obj and ***_pred.obj files in the specified directory. It is only applicable to single GPU testing and used for debugging and visualization. You do NOT need a GUI available in your environment for using this option.

All evaluation related arguments are set in the test_evaluator in corresponding dataset configuration. such as test_evaluator = dict(type='KittiMetric', ann_file=data_root + 'kitti_infos_val.pkl', pklfile_prefix=None, submission_prefix=None)

The arguments:

  • type: The name of the corresponding metric, usually associated with the dataset.

  • ann_file: The path of annotation file.

  • pklfile_prefix: An optional argument. The filename of the output results in pickle format. If not specified, the results will not be saved to a file.

  • submission_prefix: An optional argument. The results will be saved to a file then you can upload it to do the official evaluation.


Assume that you have already downloaded the checkpoints to the directory checkpoints/.

  1. Test VoteNet on ScanNet and save the points and prediction visualization results.

    python tools/ configs/votenet/ \
        checkpoints/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth \
        --show --show-dir ./data/scannet/show_results
  2. Test VoteNet on ScanNet, save the points, prediction, groundtruth visualization results, and evaluate the mAP.

    python tools/ configs/votenet/ \
        checkpoints/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth \
        --show --show-dir ./data/scannet/show_results
  3. Test VoteNet on ScanNet (without saving the test results) and evaluate the mAP.

    python tools/ configs/votenet/ \
  4. Test SECOND on KITTI with 8 GPUs, and evaluate the mAP.

    ./tools/ ${PARTITION} ${JOB_NAME} configs/second/ \
  5. Test PointPillars on nuScenes with 8 GPUs, and generate the json file to be submit to the official evaluation server.

    ./tools/ ${PARTITION} ${JOB_NAME} configs/pointpillars/ \
        checkpoints/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20200620_230405-2fa62f3d.pth \
       --cfg-options 'test_evaluator.jsonfile_prefix=./pointpillars_nuscenes_results'

    The generated results be under ./pointpillars_nuscenes_results directory.

  6. Test SECOND on KITTI with 8 GPUs, and generate the pkl files and submission data to be submit to the official evaluation server.

    ./tools/ ${PARTITION} ${JOB_NAME} configs/second/ \
        checkpoints/hv_second_secfpn_6x8_80e_kitti-3d-3class_20200620_230238-9208083a.pth \
        --cfg-options 'test_evaluator.pklfile_prefix=./second_kitti_results' 'submission_prefix=./second_kitti_results'

    The generated results be under ./second_kitti_results directory.

  7. Test PointPillars on Lyft with 8 GPUs, generate the pkl files and make a submission to the leaderboard.

    ./tools/ ${PARTITION} ${JOB_NAME} configs/pointpillars/ \
        checkpoints/hv_pointpillars_fpn_sbn-2x8_2x_lyft-3d_latest.pth \
        --cfg-options 'test_evaluator.jsonfile_prefix=results/pp_lyft/results_challenge' \
        'test_evaluator.csv_savepath=results/pp_lyft/results_challenge.csv' \

    Notice: To generate submissions on Lyft, csv_savepath must be given in the --cfg-options. After generating the csv file, you can make a submission with kaggle commands given on the website.

    Note that in the config of Lyft dataset, the value of ann_file keyword in test is 'lyft_infos_test.pkl', which is the official test set of Lyft without annotation. To test on the validation set, please change this to 'lyft_infos_val.pkl'.

  8. Test PointPillars on waymo with 8 GPUs, and evaluate the mAP with waymo metrics.

    ./tools/ ${PARTITION} ${JOB_NAME} configs/pointpillars/  \
        checkpoints/hv_pointpillars_secfpn_sbn-2x16_2x_waymo-3d-car_latest.pth \
        --cfg-options 'test_evaluator.pklfile_prefix=results/waymo-car/kitti_results' \

    Notice: For evaluation on waymo, please follow the instruction to build the binary file compute_detection_metrics_main for metrics computation and put it into mmdet3d/core/evaluation/waymo_utils/.(Sometimes when using bazel to build compute_detection_metrics_main, an error 'round' is not a member of 'std' may appear. We just need to remove the std:: before round in that file.) pklfile_prefix should be given in the --eval-options for the bin file generation. For metrics, waymo is the recommended official evaluation prototype. Currently, evaluating with choice kitti is adapted from KITTI and the results for each difficulty are not exactly the same as the definition of KITTI. Instead, most of objects are marked with difficulty 0 currently, which will be fixed in the future. The reasons of its instability include the large computation for evaluation, the lack of occlusion and truncation in the converted data, different definition of difficulty and different methods of computing average precision.

  9. Test PointPillars on waymo with 8 GPUs, generate the bin files and make a submission to the leaderboard.

    ./tools/ ${PARTITION} ${JOB_NAME} configs/pointpillars/  \
        checkpoints/hv_pointpillars_secfpn_sbn-2x16_2x_waymo-3d-car_latest.pth \
        --cfg-options 'test_evaluator.pklfile_prefix=results/waymo-car/kitti_results' \

    Notice: After generating the bin file, you can simply build the binary file create_submission and use them to create a submission file by following the instruction. For evaluation on the validation set with the eval server, you can also use the same way to generate a submission.

Train predefined models on standard datasets

MMDetection3D implements distributed training and non-distributed training, which uses MMDistributedDataParallel and MMDataParallel respectively.

All outputs (log files and checkpoints) will be saved to the working directory, which is specified by work_dir in the config file.

By default we evaluate the model on the validation set after each epoch, you can change the evaluation interval by adding the interval argument in the training config.

train_cfg = dict(type='EpochBasedTrainLoop', val_interval=1)  # This evaluate the model per 12 epoch.

Important: The default learning rate in config files is for 8 GPUs and the exact batch size is marked by the config’s file name, e.g. ‘2xb8’ means 2 samples per GPU using 8 GPUs. According to the Linear Scaling Rule, you need to set the learning rate proportional to the batch size if you use different GPUs or images per GPU, e.g., lr=0.01 for 4 GPUs * 2 img/gpu and lr=0.08 for 16 GPUs * 4 img/gpu. However, since most of the models in this repo use ADAM rather than SGD for optimization, the rule may not hold and users need to tune the learning rate by themselves.

Train with a single GPU

python tools/ ${CONFIG_FILE} [optional arguments]

If you want to specify the working directory in the command, you can add an argument --work-dir ${YOUR_WORK_DIR}.

Training with CPU (experimental)

The process of training on the CPU is consistent with single GPU training. We just need to disable GPUs before the training process.


And then run the script of train with a single GPU.


For now, most of the point cloud related algorithms rely on 3D CUDA op, which can not be trained on CPU. Some monocular 3D object detection algorithms, like FCOS3D and SMOKE can be trained on CPU. We do not recommend users to use CPU for training because it is too slow. We support this feature to allow users to debug certain models on machines without GPU for convenience.

Train with multiple GPUs

./tools/ ${CONFIG_FILE} ${GPU_NUM} [optional arguments]

Optional arguments are:

  • --cfg-options 'Key=value': Override some settings in the used config.

Train with multiple machines

If you run MMDetection3D on a cluster managed with slurm, you can use the script (This script also supports single machine training.)


Here is an example of using 16 GPUs to train Mask R-CNN on the dev partition.

GPUS=16 ./tools/ dev pp_kitti_3class configs/pointpillars/ /nfs/xxxx/pp_kitti_3class

You can check for full arguments and environment variables.

If you launch with multiple machines simply connected with ethernet, you can simply run following commands:

On the first machine:


On the second machine:


Usually it is slow if you do not have high speed networking like InfiniBand.

Launch multiple jobs on a single machine

If you launch multiple jobs on a single machine, e.g., 2 jobs of 4-GPU training on a machine with 8 GPUs, you need to specify different ports (29500 by default) for each job to avoid communication conflict.

If you use to launch training jobs, you can set the port in commands.

CUDA_VISIBLE_DEVICES=0,1,2,3 PORT=29500 ./tools/ ${CONFIG_FILE} 4
CUDA_VISIBLE_DEVICES=4,5,6,7 PORT=29501 ./tools/ ${CONFIG_FILE} 4

If you use launch training jobs with Slurm, there are two ways to specify the ports.

  1. Set the port through --cfg-options. This is more recommended since it does not change the original configs.

    CUDA_VISIBLE_DEVICES=0,1,2,3 GPUS=4 ./tools/ ${PARTITION} ${JOB_NAME} ${WORK_DIR} --cfg-options 'env_cfg.dist_cfg.port=29500'
    CUDA_VISIBLE_DEVICES=4,5,6,7 GPUS=4 ./tools/ ${PARTITION} ${JOB_NAME} ${WORK_DIR} --cfg-options 'env_cfg.dist_cfg.port=29501'
  2. Modify the config files (usually the 6th line from the bottom in config files) to set different communication ports.


    env_cfg = dict(
        dist_cfg=dict(backend='nccl', port=29500)


    env_cfg = dict(
        dist_cfg=dict(backend='nccl', port=29501)

    Then you can launch two jobs with and

Read the Docs v: latest
On Read the Docs
Project Home

Free document hosting provided by Read the Docs.