Skip to content

GitLab

Commit e8298d24 authored by zhangwenwei's avatar zhangwenwei
Browse files

Merge branch 'getting_started' into 'master' 

Getting started

See merge request open-mmlab/mmdet.3d!108
parents dd2f285b fb8f331b
Show whitespace changes
Inline Side-by-side
Showing with 29 additions and 36 deletions
configs/votenet/README.md
View file @ e8298d24
...@@ -16,9 +16,9 @@ We implement VoteNet and provide the result and checkpoints on ScanNet and SUNRG ...@@ -16,9 +16,9 @@ We implement VoteNet and provide the result and checkpoints on ScanNet and SUNRG
### ScanNet ### ScanNet
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | AP@0.25 |AP@0.5| Download | | Backbone | Lr schd | Mem (GB) | Inf time (fps) | AP@0.25 |AP@0.5| Download |
| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: | | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
| [PointNet++](./votenet_8x8_scannet-3d-18class.py) | 3x |4.1||62.90|39.91|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/votenet/votenet_16x8_sunrgbd-3d-10class/votenet_16x8_sunrgbd-3d-10class_20200620_230238-4483c0c0.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/votenet/votenet_16x8_sunrgbd-3d-10class/votenet_16x8_sunrgbd-3d-10class_20200620_230238.log.json)| | [PointNet++](./votenet_8x8_scannet-3d-18class.py) | 3x |4.1||62.90|39.91|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/votenet/votenet_8x8_scannet-3d-18class/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/votenet/votenet_8x8_scannet-3d-18class/votenet_8x8_scannet-3d-18class_20200620_230238.log.json)|
### SUNRGBD ### SUNRGBD
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | AP@0.25 |AP@0.5| Download | | Backbone | Lr schd | Mem (GB) | Inf time (fps) | AP@0.25 |AP@0.5| Download |
| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: | | :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
| [PointNet++](./votenet_16x8_sunrgbd-3d-10class.py) | 3x |8.1||59.07|35.77|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/votenet/votenet_8x8_scannet-3d-18class/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/votenet/votenet_8x8_scannet-3d-18class/votenet_8x8_scannet-3d-18class_20200620_230238.log.json)| | [PointNet++](./votenet_16x8_sunrgbd-3d-10class.py) | 3x |8.1||59.07|35.77|[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/votenet/votenet_16x8_sunrgbd-3d-10class/votenet_16x8_sunrgbd-3d-10class_20200620_230238-4483c0c0.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection3d/v0.1.0_models/votenet/votenet_16x8_sunrgbd-3d-10class/votenet_16x8_sunrgbd-3d-10class_20200620_230238.log.json)|
docs/getting_started.md
View file @ e8298d24
...@@ -117,65 +117,58 @@ Examples: ...@@ -117,65 +117,58 @@ Examples:
Assume that you have already downloaded the checkpoints to the directory `checkpoints/`. Assume that you have already downloaded the checkpoints to the directory `checkpoints/`.
1. Test Faster R-CNN and visualize the results. Press any key for the next image. 1. Test votenet on ScanNet and save the points and prediction visualization results.
```shell ```shell
python tools/test.py configs/faster_rcnn_r50_fpn_1x_coco.py \ python tools/test.py configs/votenet/votenet_8x8_scannet-3d-18class.py \
checkpoints/faster_rcnn_r50_fpn_1x_20181010-3d1b3351.pth \ checkpoints/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth \
--show --show --show-dir ./data/scannet/show_results
``` ```
2. Test Faster R-CNN and save the painted images for latter visualization. 2. Test votenet on ScanNet, save the points, prediction, groundtruth visualization results, and evaluate the mAP.
```shell ```shell
python tools/test.py configs/faster_rcnn_r50_fpn_1x.py \ python tools/test.py configs/votenet/votenet_8x8_scannet-3d-18class.py \
checkpoints/faster_rcnn_r50_fpn_1x_20181010-3d1b3351.pth \ checkpoints/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth \
--show-dir faster_rcnn_r50_fpn_1x_results
```
3. Test Faster R-CNN on PASCAL VOC (without saving the test results) and evaluate the mAP.
```shell
python tools/test.py configs/pascal_voc/faster_rcnn_r50_fpn_1x_voc.py \
checkpoints/SOME_CHECKPOINT.pth \
--eval mAP --eval mAP
--options 'show=True' 'out_dir=./data/scannet/show_results'
``` ```
4. Test Mask R-CNN with 8 GPUs, and evaluate the bbox and mask AP. 3. Test votenet on ScanNet (without saving the test results) and evaluate the mAP.
```shell ```shell
./tools/dist_test.sh configs/mask_rcnn_r50_fpn_1x_coco.py \ python tools/test.py configs/votenet/votenet_8x8_scannet-3d-18class.py \
checkpoints/mask_rcnn_r50_fpn_1x_20181010-069fa190.pth \ checkpoints/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth \
8 --out results.pkl --eval bbox segm --eval mAP
``` ```
5. Test Mask R-CNN with 8 GPUs, and evaluate the **classwise** bbox and mask AP. 4. Test SECOND with 8 GPUs, and evaluate the mAP.
```shell ```shell
./tools/dist_test.sh configs/mask_rcnn_r50_fpn_1x_coco.py \ ./tools/slurm_test.sh ${PARTITION} ${JOB_NAME} configs/second/hv_second_secfpn_6x8_80e_kitti-3d-3class.py \
checkpoints/mask_rcnn_r50_fpn_1x_20181010-069fa190.pth \ checkpoints/hv_second_secfpn_6x8_80e_kitti-3d-3class_20200620_230238-9208083a.pth \
8 --out results.pkl --eval bbox segm --options "classwise=True" --out results.pkl --eval mAP
``` ```
6. Test Mask R-CNN on COCO test-dev with 8 GPUs, and generate the json file to be submit to the official evaluation server. 5. Test PointPillars on nuscenes with 8 GPUs, and generate the json file to be submit to the official evaluation server.
```shell ```shell
./tools/dist_test.sh configs/mask_rcnn_r50_fpn_1x_coco.py \ ./tools/slurm_test.sh ${PARTITION} ${JOB_NAME} configs/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py \
checkpoints/mask_rcnn_r50_fpn_1x_20181010-069fa190.pth \ checkpoints/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20200620_230405-2fa62f3d.pth \
8 --format-only --options "jsonfile_prefix=./mask_rcnn_test-dev_results" --format-only --options 'jsonfile_prefix=./pointpillars_nuscenes_results'
``` ```
You will get two json files `mask_rcnn_test-dev_results.bbox.json` and `mask_rcnn_test-dev_results.segm.json`. The generated results be under `./pointpillars_nuscenes_results` directory.
7. Test Mask R-CNN on Cityscapes test with 8 GPUs, and generate the txt and png files to be submit to the official evaluation server. 6. Test SECOND on KITTI with 8 GPUs, and generate the pkl files and submission datas to be submit to the official evaluation server.
```shell ```shell
./tools/dist_test.sh configs/cityscapes/mask_rcnn_r50_fpn_1x_cityscapes.py \ ./tools/slurm_test.sh ${PARTITION} ${JOB_NAME} configs/second/hv_second_secfpn_6x8_80e_kitti-3d-3class.py \
checkpoints/mask_rcnn_r50_fpn_1x_cityscapes_20200227-afe51d5a.pth \ checkpoints/hv_second_secfpn_6x8_80e_kitti-3d-3class_20200620_230238-9208083a.pth \
8 --format-only --options "txtfile_prefix=./mask_rcnn_cityscapes_test_results" --format-only --options 'pklfile_prefix=./second_kitti_results' 'submission_prefix=./second_kitti_results'
``` ```
The generated png and txt would be under `./mask_rcnn_cityscapes_test_results` directory. The generated results be under `./second_kitti_results` directory.
### Visualization ### Visualization
...@@ -189,7 +182,7 @@ Aftering running this command, plotted results ***_points.obj and ***_pred.ply f ...@@ -189,7 +182,7 @@ Aftering running this command, plotted results ***_points.obj and ***_pred.ply f
To see the points, detection results and ground truth of SUNRGBD, ScanNet or KITTI during evaluation time, you can run the following command To see the points, detection results and ground truth of SUNRGBD, ScanNet or KITTI during evaluation time, you can run the following command
```bash ```bash
python tools/test.py ${CONFIG_FILE} ${CKPT_PATH} --eval 'mAP' --options "show=True" "out_dir=${SHOW_DIR}" python tools/test.py ${CONFIG_FILE} ${CKPT_PATH} --eval 'mAP' --options 'show=True' 'out_dir=${SHOW_DIR}'
``` ```
After running this command, you will obtain ***_points.ob, ***_pred.ply files and ***_gt.ply in `${SHOW_DIR}`. After running this command, you will obtain ***_points.ob, ***_pred.ply files and ***_gt.ply in `${SHOW_DIR}`.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment