@@ -18,8 +18,8 @@ It is also the official code release of [`[PointRCNN]`](https://arxiv.org/abs/18
...
@@ -18,8 +18,8 @@ It is also the official code release of [`[PointRCNN]`](https://arxiv.org/abs/18
## Changelog
## Changelog
[2020-11-10] **NEW:** The Waymo Open Dataset has been supported with SoTA results. By now we provid the
[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
configs of `SECOND`, `PartA2` and `PV-RCNN` on the Waymo Open Dataset, and more models could be easily supported by modifying their dataset configs.
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.
[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.
...
@@ -112,7 +112,7 @@ All models are trained with 8 GTX 1080Ti GPUs and are available for download.
...
@@ -112,7 +112,7 @@ All models are trained with 8 GTX 1080Ti GPUs and are available for download.
We provide the setting of `DATA_CONFIG.SAMPLED_INTERVAL` on the Waymo Open Dataset (WOD) to subsample partial samples for training and evaluation,
We provide the setting of `DATA_CONFIG.SAMPLED_INTERVAL` on the Waymo Open Dataset (WOD) to subsample partial samples for training and evaluation,
so you could also play with WOD by setting a smaller `DATA_CONFIG.SAMPLED_INTERVAL` if you only have limited GPU resources.
so you could also play with WOD by setting a smaller `DATA_CONFIG.SAMPLED_INTERVAL` if you only have limited GPU resources.
By default, all models are trained with **20% data (~32k frames)** of all the training samples, and the results of each cell here are mAP/mAPH calculated by the official Waymo evaluation metrics on the **whole** validation set.
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.
* Please download the official [Waymo Open Dataset](https://waymo.com/open/download/),
* Please download the official [Waymo Open Dataset](https://waymo.com/open/download/),
including the training data `training_0000.tar~training_0031.tar` and the validation
including the training data `training_0000.tar~training_0031.tar` and the validation
data `validation_0000.tar~validation_0007.tar`.
data `validation_0000.tar~validation_0007.tar`.
* Unzip all the above `xxxx.tar` files to the directory of `data/waymo/raw_data_v1_2` as follows (You could get 798 *train* tfrecord and 202 *val* tfrecord ):
* 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 ):
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.
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.
