`OpenPCDet` is a clear, simple, self-contained open source project for LiDAR-based 3D object detection.
It is also the official code release of [`[PointRCNN]`](https://arxiv.org/abs/1812.04244), [`[Part-A^2 net]`](https://arxiv.org/abs/1907.03670), [`[PV-RCNN]`](https://arxiv.org/abs/1912.13192) and [`[Voxel R-CNN]`](https://arxiv.org/abs/2012.15712).
It is also the official code release of [`[PointRCNN]`](https://arxiv.org/abs/1812.04244), [`[Part-A2-Net]`](https://arxiv.org/abs/1907.03670), [`[PV-RCNN]`](https://arxiv.org/abs/1912.13192) and [`[Voxel R-CNN]`](https://arxiv.org/abs/2012.15712).
**NEW**: `OpenPCDet` has been updated to `v0.5.0` (Dec. 2021).
## Overview
-[Changelog](#changelog)
...
...
@@ -18,15 +19,22 @@ It is also the official code release of [`[PointRCNN]`](https://arxiv.org/abs/18
## Changelog
[2021-12-01] **NEW:**`OpenPCDet` v0.5.0 is released with the following features:
* Improve the performance of all models on [Waymo Open Dataset](#waymo-open-dataset-baselines). Note that you need to re-prepare the training/validation data and ground-truth database of Waymo Open Dataset (see [GETTING_STARTED.md](docs/GETTING_STARTED.md)).
* Support anchor-free [CenterHead](pcdet/models/dense_heads/center_head.py), add configs of `CenterPoint` and `PV-RCNN with CenterHead`.
* Support lastest **PyTorch 1.1~1.10** and **spconv 1.0~2.x**, where **spconv 2.x** should be easy to install with pip and faster than previous version (see the official update of spconv [here](https://github.com/traveller59/spconv)).
* Support config [`USE_SHARED_MEMORY`](tools/cfgs/dataset_configs/waymo_dataset.yaml) to use shared memory to potentially speed up the training process in case you suffer from an IO problem.
* Support better and faster [visualization script](tools/visual_utils/open3d_vis_utils.py), and you need to install [Open3D](https://github.com/isl-org/Open3D) firstly.
[2021-06-08] Added support for the voxel-based 3D object detection model [`Voxel R-CNN`](#KITTI-3D-Object-Detection-Baselines)
[2021-05-14] Added support for the monocular 3D object detection model [`CaDDN`](#KITTI-3D-Object-Detection-Baselines)
[2020-11-27] **Bugfixed:** Please re-prepare the validation infos of Waymo dataset (version 1.2) if you would like to
[2020-11-27] Bugfixed: Please re-prepare the validation infos of Waymo dataset (version 1.2) if you would like to
use our provided Waymo evaluation tool (see [PR](https://github.com/open-mmlab/OpenPCDet/pull/383)).
Note that you do not need to re-prepare the training data and ground-truth database.
[2020-11-10] **NEW:** The [Waymo Open Dataset](#waymo-open-dataset-baselines) has been supported with state-of-the-art results. Currently we provide the
[2020-11-10] The [Waymo Open Dataset](#waymo-open-dataset-baselines) has been supported with state-of-the-art results. Currently we provide the
configs and results of `SECOND`, `PartA2` and `PV-RCNN` on the Waymo Open Dataset, and more models could be easily supported by modifying their dataset configs.
[2020-08-10] Bugfixed: The provided NuScenes models have been updated to fix the loading bugs. Please redownload it if you need to use the pretrained NuScenes models.
...
...
@@ -102,22 +110,15 @@ Selected supported methods are shown in the below table. The results are the 3D
We provide the setting of [`DATA_CONFIG.SAMPLED_INTERVAL`](tools/cfgs/dataset_configs/waymo_dataset.yaml) on the Waymo Open Dataset (WOD) to subsample partial samples for training and evaluation,
...
...
@@ -125,19 +126,30 @@ so you could also play with WOD by setting a smaller `DATA_CONFIG.SAMPLED_INTERV
By default, all models are trained with **20% data (~32k frames)** of all the training samples on 8 GTX 1080Ti GPUs, and the results of each cell here are mAP/mAPH calculated by the official Waymo evaluation metrics on the **whole** validation set (version 1.2).
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.
## Pretrained Models
If you would like to train [CaDDN](../tools/cfgs/kitti_models/CaDDN.yaml), download the pretrained [DeepLabV3 model](https://download.pytorch.org/models/deeplabv3_resnet101_coco-586e9e4e.pth) and place within the `checkpoints` directory
If you would like to train [CaDDN](../tools/cfgs/kitti_models/CaDDN.yaml), download the pretrained [DeepLabV3 model](https://download.pytorch.org/models/deeplabv3_resnet101_coco-586e9e4e.pth) and place within the `checkpoints` directory. Please make sure the [kornia](https://github.com/kornia/kornia) is installed since it is needed for `CaDDN`.
All the codes are tested in the following environment:
* Linux (tested on Ubuntu 14.04/16.04)
* Linux (tested on Ubuntu 14.04/16.04/18.04/20.04/21.04)
* Python 3.6+
* PyTorch 1.1 or higher (tested on PyTorch 1.1, 1,3, 1,5)
* PyTorch 1.1 or higher (tested on PyTorch 1.1, 1,3, 1,5~1.10)
* CUDA 9.0 or higher (PyTorch 1.3+ needs CUDA 9.2+)
*[`spconv v1.0 (commit 8da6f96)`](https://github.com/traveller59/spconv/tree/8da6f967fb9a054d8870c3515b1b44eca2103634) or [`spconv v1.2`](https://github.com/traveller59/spconv)
*[`spconv v1.0 (commit 8da6f96)`](https://github.com/traveller59/spconv/tree/8da6f967fb9a054d8870c3515b1b44eca2103634) or [`spconv v1.2`](https://github.com/traveller59/spconv) or [`spconv v2.x`](https://github.com/traveller59/spconv)
### Install `pcdet v0.3`
NOTE: Please re-install `pcdet v0.3` by running `python setup.py develop` even if you have already installed previous version.
### Install `pcdet v0.5`
NOTE: Please re-install `pcdet v0.5` by running `python setup.py develop` even if you have already installed previous version.
[comment]:<>(* Install the dependent python libraries: )
[comment]:<>(```)
[comment]:<>(pip install -r requirements.txt )
[comment]:<>(```)
* Install the SparseConv library, we use the implementation from [`[spconv]`](https://github.com/traveller59/spconv).
* If you use PyTorch 1.1, then make sure you install the `spconv v1.0` with ([commit 8da6f96](https://github.com/traveller59/spconv/tree/8da6f967fb9a054d8870c3515b1b44eca2103634)) instead of the latest one.
* If you use PyTorch 1.3+, then you need to install the `spconv v1.2`. As mentioned by the author of [`spconv`](https://github.com/traveller59/spconv), you need to use their docker if you use PyTorch 1.4+.
* You could also install latest `spconv v2.x` with pip, see the official documents of [spconv](https://github.com/traveller59/spconv).
c. Install this `pcdet` library by running the following command:
c. Install this `pcdet` library and its dependent libraries by running the following command:
# Note: Kornia team will fix this import issue to try to allow the usage of lower torch versions.
print('Warning: kornia is not installed correctly, please ignore this warning if you do not use CaDDN. Otherwise, it is recommended to use torch version greater than 1.2 to use kornia properly.')
# print('Warning: kornia is not installed correctly, please ignore this warning if you do not use CaDDN. Otherwise, it is recommended to use torch version greater than 1.2 to use kornia properly.')
pass
frompcdet.utilsimporttransform_utils
...
...
@@ -22,6 +23,14 @@ class FrustumGridGenerator(nn.Module):
