Merge branch 'fix-doc-tweaks' into 'master'

Update tweaks in documentation

See merge request open-mmlab/mmdet.3d!131

docs/api.rst

@@ -71,22 +71,22 @@ roi_heads
     :members:
 
 roi_heads.bbox_heads
-^^^^^^^^^^
+^^^^^^^^^^^^^^^^^^^^
 .. automodule:: mmdet3d.models.roi_heads.bbox_heads
     :members:
 
 roi_heads.mask_heads
-^^^^^^^^^^
+^^^^^^^^^^^^^^^^^^^^
 .. automodule:: mmdet3d.models.roi_heads.mask_heads
     :members:
 
 roi_heads.roi_extractors
-^^^^^^^^^^
+^^^^^^^^^^^^^^^^^^^^^^^^^
 .. automodule:: mmdet3d.models.roi_heads.roi_extractors
     :members:
 
 fusion_layers
-^^^^^^^^^^
+^^^^^^^^^^^^^
 .. automodule:: mmdet3d.models.fusion_layers
     :members:
 
@@ -96,11 +96,11 @@ losses
     :members:
 
 middle_encoders
-^^^^^^^^^^
+^^^^^^^^^^^^^^^
 .. automodule:: mmdet3d.models.middle_encoders
     :members:
 
 model_utils
-^^^^^^^^^^
+^^^^^^^^^^^^^
 .. automodule:: mmdet3d.models.model_utils
     :members:

docs/benchmarks.md

@@ -24,7 +24,7 @@ We compare our implementation of VoteNet with [votenet](https://github.com/faceb
 +================+=====================+====================+========+
 | MMDetection3D  |        358          |         17         |  35.8  |
 +----------------+---------------------+--------------------+--------+
-| votenet_       |        77           |         3          |  31.5  |
+| votenet        |        77           |         3          |  31.5  |
 +----------------+---------------------+--------------------+--------+
 
 ```
@@ -47,13 +47,13 @@ performance on 3 classes.
 ```
 
 ```eval_rst
-  +----------------+---------------------+--------------------+
-  | Implementation | Training (sample/s) | Testing (sample/s) |
-  +================+=====================+====================+
-  | MMDetection3D  |         107         |        45          |
-  +----------------+---------------------+--------------------+
-  | OpenPCDet      |         44          |        25          |
-  +----------------+---------------------+--------------------+
++----------------+---------------------+--------------------+
+| Implementation | Training (sample/s) | Testing (sample/s) |
++================+=====================+====================+
+| MMDetection3D  |         107         |        45          |
++----------------+---------------------+--------------------+
+| OpenPCDet      |         44          |        25          |
++----------------+---------------------+--------------------+
 ```
 
 ### SECOND
@@ -63,36 +63,36 @@ So we only compare with [OpenPCDet](https://github.com/open-mmlab/OpenPCDet/tree
 condition following the KITTI benchmark and compare average AP over all classes on moderate condition for
 performance on 3 classes.
 
-  ```eval_rst
-    +----------------+---------------------+--------------------+
-    | Implementation | Training (sample/s) | Testing (sample/s) |
-    +================+=====================+====================+
-    | MMDetection3D  |         40          |         27         |
-    +----------------+---------------------+--------------------+
-    | OpenPCDet      |         30          |         32         |
-    +----------------+---------------------+--------------------+
-  ```
+```eval_rst
++----------------+---------------------+--------------------+
+| Implementation | Training (sample/s) | Testing (sample/s) |
++================+=====================+====================+
+| MMDetection3D  |         40          |         27         |
++----------------+---------------------+--------------------+
+| OpenPCDet      |         30          |         32         |
++----------------+---------------------+--------------------+
+```
 
 ### Part-A2
 
 We benchmark Part-A2 with that in [OpenPCDet](https://github.com/open-mmlab/OpenPCDet/tree/b32fbddbe06183507bad433ed99b407cbc2175c2). We report the AP on moderate condition following the KITTI benchmark
 and compare average AP over all classes on moderate condition for performance on 3 classes.
 
-  ```eval_rst
-    +----------------+---------------------+--------------------+
-    | Implementation | Training (sample/s) | Testing (sample/s) |
-    +================+=====================+====================+
-    | MMDetection3D  |         17          |         11         |
-    +----------------+---------------------+--------------------+
-    | OpenPCDet      |         14          |         13         |
-    +----------------+---------------------+--------------------+
-  ```
+```eval_rst
++----------------+---------------------+--------------------+
+| Implementation | Training (sample/s) | Testing (sample/s) |
++================+=====================+====================+
+| MMDetection3D  |         17          |         11         |
++----------------+---------------------+--------------------+
+| OpenPCDet      |         14          |         13         |
++----------------+---------------------+--------------------+
+```
 
 ## Details of Comparison
 
 ### Modification for Calculating Speed
 
-* __Det3D__: At commit 255c593
+* __Det3D__: At commit [255c593]()
 
 * __OpenPCDet__: At commit [b32fbddb](https://github.com/open-mmlab/OpenPCDet/tree/b32fbddbe06183507bad433ed99b407cbc2175c2)
 

docs/conf.py

@@ -12,6 +12,8 @@
 #
 import os
 import sys
+from m2r import MdInclude
+from recommonmark.transform import AutoStructify
 
 sys.path.insert(0, os.path.abspath('..'))
 
@@ -36,6 +38,7 @@ extensions = [
     'sphinx.ext.viewcode',
     'recommonmark',
     'sphinx_markdown_tables',
+    'sphinx.ext.autosectionlabel',
 ]
 
 autodoc_mock_imports = [
@@ -46,6 +49,7 @@ autodoc_mock_imports = [
     'mmdet3d.ops.interpolate', 'mmdet3d.ops.roiaware_pool3d',
     'mmdet3d.ops.spconv', 'mmdet3d.ops.voxel.voxel_layer', 'mmdet3d.ops.iou3d'
 ]
+autosectionlabel_prefix_document = True
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
@@ -77,3 +81,16 @@ html_theme = 'sphinx_rtd_theme'
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
 html_static_path = ['_static']
+
+
+def setup(app):
+    app.add_config_value('no_underscore_emphasis', False, 'env')
+    app.add_config_value('m2r_parse_relative_links', False, 'env')
+    app.add_config_value('m2r_anonymous_references', False, 'env')
+    app.add_config_value('m2r_disable_inline_math', False, 'env')
+    app.add_directive('mdinclude', MdInclude)
+    app.add_config_value('recommonmark_config', {
+        'auto_toc_tree_section': 'Contents',
+        'enable_eval_rst': True,
+    }, True)
+    app.add_transform(AutoStructify)
\ No newline at end of file

docs/config.md

@@ -50,7 +50,7 @@ For `20e`, initial learning rate decays by a factor of 10 at the 16th and 19th e
 Sometimes, you may set `_delete_=True` to ignore some of fields in base configs.
 You may refer to [mmcv](https://mmcv.readthedocs.io/en/latest/utils.html#inherit-from-base-config-with-ignored-fields) for simple inllustration.
 
-In MMDetection, for example, to change the backbone of Mask R-CNN with the following config.
+In MMDetection or MMDetection3D, for example, to change the backbone of Mask R-CNN with the following config.
 
 ```python
 model = dict(

docs/getting_started.md

@@ -63,25 +63,28 @@ mmdetection3d
 ```
 
 Download nuScenes V1.0 full dataset data [HERE]( https://www.nuscenes.org/download). Prepare nuscenes data by running
+
 ```bash
 python tools/create_data.py nuscenes --root-path ./data/nuscenes --out-dir ./data/nuscenes --extra-tag nuscenes
 ```
 
 Download KITTI 3D detection data [HERE](http://www.cvlibs.net/datasets/kitti/eval_object.php?obj_benchmark=3d). Prepare kitti data by running
+
 ```bash
 python tools/create_data.py kitti --root-path ./data/kitti --out-dir ./data/kitti --extra-tag kitti
 ```
 
 Download Lyft 3D detection data [HERE](https://www.kaggle.com/c/3d-object-detection-for-autonomous-vehicles/data). Prepare Lyft data by running
+
 ```bash
 python tools/create_data.py lyft --root-path ./data/lyft --out-dir ./data/lyft --extra-tag lyft --version v1.01
 ```
-Note that we follow the original folder names for clear organization. Please rename the raw folders as shown above.
 
-To prepare scannet data, please see [scannet](../data/scannet/README.md).
+Note that we follow the original folder names for clear organization. Please rename the raw folders as shown above.
 
-To prepare sunrgbd data, please see [sunrgbd](../data/sunrgbd/README.md).
+To prepare scannet data, please see [scannet](https://github.com/open-mmlab/mmdetection3d/data/scannet/README.md).
 
+To prepare sunrgbd data, please see [sunrgbd](https://github.com/open-mmlab/mmdetection3d/data/sunrgbd/README.md).
 
 For using custom datasets, please refer to [Tutorials 2: Adding New Dataset](tutorials/new_dataset.md).
 
@@ -112,71 +115,70 @@ 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.ply` 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.
 
-
 Examples:
 
 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.
 
-```shell
-python tools/test.py configs/votenet/votenet_8x8_scannet-3d-18class.py \
-    checkpoints/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth \
-    --show --show-dir ./data/scannet/show_results
-```
+   ```shell
+   python tools/test.py configs/votenet/votenet_8x8_scannet-3d-18class.py \
+       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.
 
-```shell
-python tools/test.py configs/votenet/votenet_8x8_scannet-3d-18class.py \
-    checkpoints/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth \
-    --eval mAP
-    --options 'show=True' 'out_dir=./data/scannet/show_results'
-```
+   ```shell
+   python tools/test.py configs/votenet/votenet_8x8_scannet-3d-18class.py \
+       checkpoints/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth \
+       --eval mAP
+       --options 'show=True' 'out_dir=./data/scannet/show_results'
+   ```
 
 3. Test votenet on ScanNet (without saving the test results) and evaluate the mAP.
 
-```shell
-python tools/test.py configs/votenet/votenet_8x8_scannet-3d-18class.py \
-    checkpoints/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth \
-    --eval mAP
-```
+   ```shell
+   python tools/test.py configs/votenet/votenet_8x8_scannet-3d-18class.py \
+       checkpoints/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth \
+       --eval mAP
+   ```
 
 4. Test SECOND with 8 GPUs, and evaluate the mAP.
 
-```shell
-./tools/slurm_test.sh ${PARTITION} ${JOB_NAME} configs/second/hv_second_secfpn_6x8_80e_kitti-3d-3class.py \
-    checkpoints/hv_second_secfpn_6x8_80e_kitti-3d-3class_20200620_230238-9208083a.pth \
-    --out results.pkl --eval mAP
-```
+   ```shell
+   ./tools/slurm_test.sh ${PARTITION} ${JOB_NAME} configs/second/hv_second_secfpn_6x8_80e_kitti-3d-3class.py \
+       checkpoints/hv_second_secfpn_6x8_80e_kitti-3d-3class_20200620_230238-9208083a.pth \
+       --out results.pkl --eval mAP
+   ```
 
 5. Test PointPillars on nuscenes with 8 GPUs, and generate the json file to be submit to the official evaluation server.
 
-```shell
-./tools/slurm_test.sh ${PARTITION} ${JOB_NAME} configs/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py \
-    checkpoints/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20200620_230405-2fa62f3d.pth \
-    --format-only --options 'jsonfile_prefix=./pointpillars_nuscenes_results'
-```
+   ```shell
+   ./tools/slurm_test.sh ${PARTITION} ${JOB_NAME} configs/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py \
+       checkpoints/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20200620_230405-2fa62f3d.pth \
+       --format-only --options 'jsonfile_prefix=./pointpillars_nuscenes_results'
+   ```
 
-The generated results be under `./pointpillars_nuscenes_results` directory.
+   The generated results be under `./pointpillars_nuscenes_results` directory.
 
 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
-./tools/slurm_test.sh ${PARTITION} ${JOB_NAME} configs/second/hv_second_secfpn_6x8_80e_kitti-3d-3class.py \
-    checkpoints/hv_second_secfpn_6x8_80e_kitti-3d-3class_20200620_230238-9208083a.pth \
-    --format-only --options 'pklfile_prefix=./second_kitti_results' 'submission_prefix=./second_kitti_results'
-```
+   ```shell
+   ./tools/slurm_test.sh ${PARTITION} ${JOB_NAME} configs/second/hv_second_secfpn_6x8_80e_kitti-3d-3class.py \
+       checkpoints/hv_second_secfpn_6x8_80e_kitti-3d-3class_20200620_230238-9208083a.pth \
+       --format-only --options 'pklfile_prefix=./second_kitti_results' 'submission_prefix=./second_kitti_results'
+   ```
 
-The generated results be under `./second_kitti_results` directory.
+   The generated results be under `./second_kitti_results` directory.
 
 ### Visualization
 
 To see the SUNRGBD, ScanNet or KITTI points and detection results, you can run the following command
 
- ```bash
- python tools/test.py ${CONFIG_FILE} ${CKPT_PATH} --show --show-dir ${SHOW_DIR}
-  ```
+```bash
+python tools/test.py ${CONFIG_FILE} ${CKPT_PATH} --show --show-dir ${SHOW_DIR}
+```
 
 Aftering running this command, plotted results ***_points.obj and ***_pred.ply files in `${SHOW_DIR}`.
 
@@ -202,7 +204,7 @@ Examples:
 
 ```shell
 python demo/pcd_demo.py demo/kitti_000008.bin configs/second/hv_second_secfpn_6x8_80e_kitti-3d-car.py \
-    checkpoints/epoch_40.pth
+    checkpoints/hv_second_secfpn_6x8_80e_kitti-3d-3class_20200620_230238-9208083a.pth
 ```
 
 
@@ -238,49 +240,6 @@ for frame in video:
 
 A notebook demo can be found in [demo/inference_demo.ipynb](https://github.com/open-mmlab/mmdetection/blob/master/demo/inference_demo.ipynb).
 
-#### Asynchronous interface - supported for Python 3.7+
-
-Async interface allows not to block CPU on GPU bound inference code and enables better CPU/GPU utilization for single threaded application. Inference can be done concurrently either between different input data samples or between different models of some inference pipeline.
-
-See `tests/async_benchmark.py` to compare the speed of synchronous and asynchronous interfaces.
-
-```python
-import asyncio
-import torch
-from mmdet.apis import init_detector, async_inference_detector
-from mmdet.utils.contextmanagers import concurrent
-
-async def main():
-    config_file = 'configs/faster_rcnn_r50_fpn_1x_coco.py'
-    checkpoint_file = 'checkpoints/faster_rcnn_r50_fpn_1x_20181010-3d1b3351.pth'
-    device = 'cuda:0'
-    model = init_detector(config_file, checkpoint=checkpoint_file, device=device)
-
-    # queue is used for concurrent inference of multiple images
-    streamqueue = asyncio.Queue()
-    # queue size defines concurrency level
-    streamqueue_size = 3
-
-    for _ in range(streamqueue_size):
-        streamqueue.put_nowait(torch.cuda.Stream(device=device))
-
-    # test a single image and show the results
-    img = 'test.jpg'  # or img = mmcv.imread(img), which will only load it once
-
-    async with concurrent(streamqueue):
-        result = await async_inference_detector(model, img)
-
-    # visualize the results in a new window
-    model.show_result(img, result)
-    # or save the visualization results to image files
-    model.show_result(img, result, out_file='result.jpg')
-
-
-asyncio.run(main())
-
-```
-
-
 ## Train a model
 
 MMDetection implements distributed training and non-distributed training,
@@ -294,7 +253,7 @@ By default we evaluate the model on the validation set after each epoch, you can
 evaluation = dict(interval=12)  # This evaluate the model per 12 epoch.
 ```
 
-**\*Important\***: The default learning rate in config files is for 8 GPUs and 2 img/gpu (batch size = 8*2 = 16).
+**\*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. '2x8' means 2 samples per GPU using 8 GPUs.
 According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), 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.
 
 ### Train with a single GPU
@@ -316,6 +275,7 @@ Optional arguments are:
 - `--no-validate` (**not suggested**): By default, the codebase will perform evaluation at every k (default value is 1, which can be modified like [this](https://github.com/open-mmlab/mmdetection/blob/master/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py#L174)) epochs during the training. To disable this behavior, use `--no-validate`.
 - `--work-dir ${WORK_DIR}`: Override the working directory specified in the config file.
 - `--resume-from ${CHECKPOINT_FILE}`: Resume from a previous checkpoint file.
+- `--options 'Key=value'`: Overide some settings in the used config.
 
 Difference between `resume-from` and `load-from`:
 `resume-from` loads both the model weights and optimizer status, and the epoch is also inherited from the specified checkpoint. It is usually used for resuming the training process that is interrupted accidentally.
@@ -353,24 +313,35 @@ CUDA_VISIBLE_DEVICES=0,1,2,3 PORT=29500 ./tools/dist_train.sh ${CONFIG_FILE} 4
 CUDA_VISIBLE_DEVICES=4,5,6,7 PORT=29501 ./tools/dist_train.sh ${CONFIG_FILE} 4
 ```
 
-If you use launch training jobs with Slurm, you need to modify the config files (usually the 6th line from the bottom in config files) to set different communication ports.
+If you use launch training jobs with Slurm, there are two ways to specify the ports.
 
-In `config1.py`,
-```python
-dist_params = dict(backend='nccl', port=29500)
-```
+1. Modify the config files (usually the 6th line from the bottom in config files) to set different communication ports.
 
-In `config2.py`,
-```python
-dist_params = dict(backend='nccl', port=29501)
-```
+   In `config1.py`,
 
-Then you can launch two jobs with `config1.py` ang `config2.py`.
+   ```python
+   dist_params = dict(backend='nccl', port=29500)
+   ```
 
-```shell
-CUDA_VISIBLE_DEVICES=0,1,2,3 GPUS=4 ./tools/slurm_train.sh ${PARTITION} ${JOB_NAME} config1.py ${WORK_DIR}
-CUDA_VISIBLE_DEVICES=4,5,6,7 GPUS=4 ./tools/slurm_train.sh ${PARTITION} ${JOB_NAME} config2.py ${WORK_DIR}
-```
+   In `config2.py`,
+
+   ```python
+   dist_params = dict(backend='nccl', port=29501)
+   ```
+
+   Then you can launch two jobs with `config1.py` ang `config2.py`.
+
+   ```shell
+   CUDA_VISIBLE_DEVICES=0,1,2,3 GPUS=4 ./tools/slurm_train.sh ${PARTITION} ${JOB_NAME} config1.py ${WORK_DIR}
+   CUDA_VISIBLE_DEVICES=4,5,6,7 GPUS=4 ./tools/slurm_train.sh ${PARTITION} ${JOB_NAME} config2.py ${WORK_DIR}
+   ```
+
+2. Set the port through `--options`. This is more recommended since it does not change the original configs.
+
+   ```shell
+   CUDA_VISIBLE_DEVICES=0,1,2,3 GPUS=4 ./tools/slurm_train.sh ${PARTITION} ${JOB_NAME} config1.py ${WORK_DIR} --options 'dist_params.port=29500'
+   CUDA_VISIBLE_DEVICES=4,5,6,7 GPUS=4 ./tools/slurm_train.sh ${PARTITION} ${JOB_NAME} config2.py ${WORK_DIR} --options 'dist_params.port=29501'
+   ```
 
 ## Useful tools
 
@@ -390,21 +361,21 @@ Examples:
 
 - Plot the classification loss of some run.
 
-```shell
-python tools/analyze_logs.py plot_curve log.json --keys loss_cls --legend loss_cls
-```
+  ```shell
+  python tools/analyze_logs.py plot_curve log.json --keys loss_cls --legend loss_cls
+  ```
 
 - Plot the classification and regression loss of some run, and save the figure to a pdf.
 
-```shell
-python tools/analyze_logs.py plot_curve log.json --keys loss_cls loss_bbox --out losses.pdf
-```
+  ```shell
+  python tools/analyze_logs.py plot_curve log.json --keys loss_cls loss_bbox --out losses.pdf
+  ```
 
 - Compare the bbox mAP of two runs in the same figure.
 
-```shell
-python tools/analyze_logs.py plot_curve log1.json log2.json --keys bbox_mAP --legend run1 run2
-```
+  ```shell
+  python tools/analyze_logs.py plot_curve log1.json log2.json --keys bbox_mAP --legend run1 run2
+  ```
 
 You can also compute the average training speed.
 
@@ -441,20 +412,6 @@ python tools/publish_model.py work_dirs/faster_rcnn/latest.pth faster_rcnn_r50_f
 
 The final output filename will be `faster_rcnn_r50_fpn_1x_20190801-{hash id}.pth`.
 
-### Test the robustness of detectors
-
-Please refer to [robustness_benchmarking.md](robustness_benchmarking.md).
-
-### Convert to ONNX (experimental)
-
-We provide a script to convert model to [ONNX](https://github.com/onnx/onnx) format. The converted model could be visualized by tools like [Netron](https://github.com/lutzroeder/netron).
-
-```shell
-python tools/pytorch2onnx.py ${CONFIG_FILE} ${CHECKPOINT_FILE} --out ${ONNX_FILE} [--shape ${INPUT_SHAPE}]
-```
-
-**Note**: This tool is still experimental. Customized operators are not supported for now. We set `use_torchvision=True` on-the-fly for `RoIPool` and `RoIAlign`.
-
 ## Tutorials
 
 Currently, we provide four tutorials for users to [finetune models](tutorials/finetune.md), [add new dataset](tutorials/new_dataset.md), [design data pipeline](tutorials/data_pipeline.md) and [add new modules](tutorials/new_modules.md).

docs/tutorials/data_pipeline.md

@@ -38,24 +38,14 @@ test_pipeline = [
     dict(
         type='MultiScaleFlipAug',
         img_scale=(1333, 800),
-        pts_scale_ratio=1.0,
         flip=False,
-        pcd_horizontal_flip=False,
-        pcd_vertical_flip=False,
         transforms=[
-            dict(
-                type='GlobalRotScaleTrans',
-                rot_range=[0, 0],
-                scale_ratio_range=[1., 1.],
-                translation_std=[0, 0, 0]),
-            dict(type='RandomFlip3D'),
-            dict(
-                type='PointsRangeFilter', point_cloud_range=point_cloud_range),
-            dict(
-                type='DefaultFormatBundle3D',
-                class_names=class_names,
-                with_label=False),
-            dict(type='Collect3D', keys=['points'])
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
         ])
 ]
 ```
@@ -127,13 +117,12 @@ For each operation, we list the related dict fields that are added/updated/remov
 - update: img, proposals, gt_bboxes, gt_bboxes_ignore, gt_labels, gt_masks, gt_semantic_seg
 
 `Collect`
-- add: img_metas (the keys of img_metas is specified by `meta_keys`)
+- add: img_meta (the keys of img_meta is specified by `meta_keys`)
 - remove: all other keys except for those specified by `keys`
 
 ### Test time augmentation
 
-`MultiScaleFlipAug3D`
-- update: all the dict fields (update values to the collection of augmented data)
+`MultiScaleFlipAug`
 
 ## Extend and use custom pipelines
 

docs/tutorials/finetune.md

 # Tutorial 1: Finetuning Models
 
 Detectors pre-trained on the COCO dataset can serve as a good pre-trained model for other datasets, e.g., CityScapes and KITTI Dataset.
-This tutorial provides instruction for users to use the models provided in the [Model Zoo](../model_zoo.md) for other datasets to obatin better performance.
+This tutorial provides instruction for users to use the models provided in the [Model Zoo](../model_zoo.md) for other datasets to obtain better performance.
 
 There are two steps to finetune a model on a new dataset.
 - Add support for the new dataset following [Tutorial 2: Adding New Dataset](new_dataset.md).
@@ -11,7 +11,7 @@ There are two steps to finetune a model on a new dataset.
 Take the finetuning process on Cityscapes Dataset as an example, the users need to modify five parts in the config.
 
 ## Inherit base configs
-To release the burdun and reduce bugs in writing the whole configs, MMDetection V2.0 support inheriting configs from multiple existing configs. To finetune a Mask RCNN model, the new config needs to inherit
+To release the burden and reduce bugs in writing the whole configs, MMDetection V2.0 support inheriting configs from multiple existing configs. To finetune a Mask RCNN model, the new config needs to inherit
 `_base_/models/mask_rcnn_r50_fpn.py` to build the basic structure of the model. To use the Cityscapes Dataset, the new config can also simply inherit `_base_/datasets/cityscapes_instance.py`. For runtime settings such as training schedules, the new config needs to inherit `_base_/default_runtime.py`. This configs are in the `configs` directory and the users can also choose to write the whole contents rather than use inheritance.
 
 ```python
@@ -34,8 +34,10 @@ model = dict(
             fc_out_channels=1024,
             roi_feat_size=7,
             num_classes=8,
-            target_means=[0., 0., 0., 0.],
-            target_stds=[0.1, 0.1, 0.2, 0.2],
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0., 0., 0., 0.],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
             reg_class_agnostic=False,
             loss_cls=dict(
                 type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),

docs/tutorials/new_dataset.md

@@ -215,7 +215,7 @@ Currently it supports to concat and repeat datasets.
 
 ### Repeat dataset
 
-We use `RepeatDataset` as warpper to repeat the dataset. For example, suppose the original dataset is `Dataset_A`, to repeat it, the config looks like the following
+We use `RepeatDataset` as wrapper to repeat the dataset. For example, suppose the original dataset is `Dataset_A`, to repeat it, the config looks like the following
 ```python
 dataset_A_train = dict(
         type='RepeatDataset',
@@ -228,7 +228,26 @@ dataset_A_train = dict(
     )
 ```
 
-### Concatemate dataset
+### Class balanced dataset
+
+We use `ClassBalancedDataset` as wrapper to repeat the dataset based on category
+frequency. The dataset to repeat needs to instantiate function `self.get_cat_ids(idx)`
+to support `ClassBalancedDataset`.
+For example, to repeat `Dataset_A` with `oversample_thr=1e-3`, the config looks like the following
+```python
+dataset_A_train = dict(
+        type='ClassBalancedDataset',
+        oversample_thr=1e-3,
+        dataset=dict(  # This is the original config of Dataset_A
+            type='Dataset_A',
+            ...
+            pipeline=train_pipeline
+        )
+    )
+```
+You may refer to [source code](../../mmdet/datasets/dataset_wrappers.py) for details.
+
+### Concatenate dataset
 
 There two ways to concatenate the dataset.
 

docs/tutorials/new_modules.md

@@ -2,18 +2,18 @@
 
 ## Customize optimizer
 
-An example of customized optimizer `CopyOfSGD` is defined in `mmdet/core/optimizer/copy_of_sgd.py`.
-More generally, a customized optimizer could be defined as following.
+A customized optimizer could be defined as following.
 
 Assume you want to add a optimizer named as `MyOptimizer`, which has arguments `a`, `b`, and `c`.
-You need to first implement the new optimizer in a file, e.g., in `mmdet/core/optimizer/my_optimizer.py`:
+You need to create a new directory named `mmdet/core/optimizer`.
+And then implement the new optimizer in a file, e.g., in `mmdet/core/optimizer/my_optimizer.py`:
 
 ```python
 from .registry import OPTIMIZERS
 from torch.optim import Optimizer
 
 
-@OPTIMIZERS.register_module
+@OPTIMIZERS.register_module()
 class MyOptimizer(Optimizer):
 
     def __init__(self, a, b, c)
@@ -49,16 +49,16 @@ The users can directly set arguments following the [API doc](https://pytorch.org
 Some models may have some parameter-specific settings for optimization, e.g. weight decay for BatchNoarm layers.
 The users can do those fine-grained parameter tuning through customizing optimizer constructor.
 
-```
+```python
 from mmcv.utils import build_from_cfg
 
-from mmdet.core.optimizer import OPTIMIZER_BUILDERS, OPTIMIZERS
+from mmcv.runner.optimizer import OPTIMIZER_BUILDERS, OPTIMIZERS
 from mmdet.utils import get_root_logger
-from .cocktail_optimizer import CocktailOptimizer
+from .my_optimizer import MyOptimizer
 
 
-@OPTIMIZER_BUILDERS.register_module
-class CocktailOptimizerConstructor(object):
+@OPTIMIZER_BUILDERS.register_module()
+class MyOptimizerConstructor(object):
 
     def __init__(self, optimizer_cfg, paramwise_cfg=None):
 
@@ -90,7 +90,7 @@ import torch.nn as nn
 from ..registry import BACKBONES
 
 
-@BACKBONES.register_module
+@BACKBONES.register_module()
 class MobileNet(nn.Module):
 
     def __init__(self, arg1, arg2):
@@ -172,7 +172,7 @@ Double Head R-CNN implements a new bbox head for object detection.
 To implement a bbox head, basically we need to implement three functions of the new module as the following.
 
 ```python
-@HEADS.register_module
+@HEADS.register_module()
 class DoubleConvFCBBoxHead(BBoxHead):
     r"""Bbox head used in Double-Head R-CNN
 
@@ -214,7 +214,7 @@ from .base_roi_head import BaseRoIHead
 from .test_mixins import BBoxTestMixin, MaskTestMixin
 
 
-@HEADS.register_module
+@HEADS.register_module()
 class StandardRoIHead(BaseRoIHead, BBoxTestMixin, MaskTestMixin):
     """Simplest base roi head including one bbox head and one mask head.
     """
@@ -268,7 +268,7 @@ from ..builder import HEADS
 from .standard_roi_head import StandardRoIHead
 
 
-@HEADS.register_module
+@HEADS.register_module()
 class DoubleHeadRoIHead(StandardRoIHead):
     """RoI head for Double Head RCNN
 
@@ -353,7 +353,7 @@ def my_loss(pred, target):
     loss = torch.abs(pred - target)
     return loss
 
-@LOSSES.register_module
+@LOSSES.register_module()
 class MyLoss(nn.Module):
 
     def __init__(self, reduction='mean', loss_weight=1.0):

tools/print_config.py

+import argparse
+
+from mmcv import Config, DictAction
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='Print the whole config')
+    parser.add_argument('config', help='config file path')
+    parser.add_argument(
+        '--options', nargs='+', action=DictAction, help='arguments in dict')
+    args = parser.parse_args()
+
+    return args
+
+
+def main():
+    args = parse_args()
+
+    cfg = Config.fromfile(args.config)
+    if args.options is not None:
+        cfg.merge_from_dict(args.options)
+    print(f'Config:\n{cfg.pretty_text}')
+
+
+if __name__ == '__main__':
+    main()