Merge branch 'fix_docs' into 'master'

Fix docs and inference show results

See merge request open-mmlab/mmdet.3d!132

docs/benchmarks.md

@@ -243,6 +243,7 @@ and compare average AP over all classes on moderate condition for performance on
   ```
 
   Then benchmark the test speed by running
+
   ```bash
 
   ```
@@ -254,8 +255,10 @@ and compare average AP over all classes on moderate condition for performance on
   ```
 
   Then benchmark the test speed by running
-  ```bash
 
+  ```bash
+  cd tools
+  ./scripts/slurm_train.sh ${PARTITION} ${JOB_NAME} 8  --cfg_file ./cfgs/pointpillar.yaml --batch_size 32  --workers 32
   ```
 
 ### Single-class PointPillars
@@ -267,6 +270,7 @@ and compare average AP over all classes on moderate condition for performance on
   ```
 
   Then benchmark the test speed by running
+
   ```bash
 
   ```
@@ -306,6 +310,7 @@ and compare average AP over all classes on moderate condition for performance on
   </details>
 
   Then benchmark the test speed by running
+
   ```bash
 
   ```
@@ -319,6 +324,7 @@ and compare average AP over all classes on moderate condition for performance on
   ```
 
   Then benchmark the test speed by running
+
   ```bash
 
   ```
@@ -331,6 +337,7 @@ and compare average AP over all classes on moderate condition for performance on
   ```
 
   Then benchmark the test speed by running
+
   ```bash
 
   ```
@@ -344,6 +351,7 @@ and compare average AP over all classes on moderate condition for performance on
   ```
 
   Then benchmark the test speed by running
+
   ```bash
 
   ```
@@ -352,10 +360,11 @@ and compare average AP over all classes on moderate condition for performance on
 
   ```bash
   cd tools
-  sh scripts/slurm_train.sh ${PARTITION} ${JOB_NAME} 8  --cfg_file ./cfgs/second.yaml --batch_size 32  --workers 32
+  ./scripts/slurm_train.sh ${PARTITION} ${JOB_NAME} 8  --cfg_file ./cfgs/second.yaml --batch_size 32  --workers 32
   ```
 
   Then benchmark the test speed by running
+
   ```bash
 
   ```
@@ -369,6 +378,7 @@ and compare average AP over all classes on moderate condition for performance on
   ```
 
   Then benchmark the test speed by running
+
   ```bash
 
   ```
@@ -377,10 +387,11 @@ and compare average AP over all classes on moderate condition for performance on
 
   ```bash
   cd tools
-  sh scripts/slurm_train.sh ${PARTITION} ${JOB_NAME} 8  --cfg_file ./cfgs/PartA2.yaml --batch_size 32 --workers 32
+  ./scripts/slurm_train.sh ${PARTITION} ${JOB_NAME} 8  --cfg_file ./cfgs/PartA2.yaml --batch_size 32 --workers 32
   ```
 
   Then benchmark the test speed by running
+
   ```bash
 
   ```

docs/getting_started.md

@@ -90,7 +90,7 @@ For using custom datasets, please refer to [Tutorials 2: Adding New Dataset](tut
 
 ## Inference with pretrained models
 
-We provide testing scripts to evaluate a whole dataset (COCO, PASCAL VOC, Cityscapes, etc.),
+We provide testing scripts to evaluate a whole dataset (SUNRGBD, ScanNet, KITTI, etc.),
 and also some high-level apis for easier integration to other projects.
 
 ### Test a dataset
@@ -208,34 +208,25 @@ python demo/pcd_demo.py demo/kitti_000008.bin configs/second/hv_second_secfpn_6x
 ```
 
 
-### High-level APIs for testing images
+### High-level APIs for testing point clouds
 
 #### Synchronous interface
-Here is an example of building the model and test given images.
+Here is an example of building the model and test given point clouds.
 
 ```python
-from mmdet.apis import init_detector, inference_detector
-import mmcv
+from mmdet3d.apis import init_detector, inference_detector
 
-config_file = 'configs/faster_rcnn_r50_fpn_1x_coco.py'
-checkpoint_file = 'checkpoints/faster_rcnn_r50_fpn_1x_20181010-3d1b3351.pth'
+config_file = 'configs/votenet/votenet_8x8_scannet-3d-18class.py'
+checkpoint_file = 'checkpoints/votenet_8x8_scannet-3d-18class_20200620_230238-2cea9c3a.pth'
 
 # build the model from a config file and a checkpoint file
 model = init_detector(config_file, checkpoint_file, device='cuda:0')
 
 # test a single image and show the results
-img = 'test.jpg'  # or img = mmcv.imread(img), which will only load it once
-result = 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')
-
-# test a video and show the results
-video = mmcv.VideoReader('video.mp4')
-for frame in video:
-    result = inference_detector(model, frame)
-    model.show_result(frame, result, wait_time=1)
+point_cloud = 'test.bin'
+result, data = inference_detector(model, point_cloud)
+# visualize the results and save the results in 'results' folder
+model.show_results(data, result, out_dir='results')
 ```
 
 A notebook demo can be found in [demo/inference_demo.ipynb](https://github.com/open-mmlab/mmdetection/blob/master/demo/inference_demo.ipynb).

mmdet3d/models/detectors/base.py

 import copy
+import mmcv
+import torch
+from mmcv.parallel import DataContainer as DC
 from os import path as osp
 
 from mmdet3d.core import Box3DMode, show_result
@@ -66,21 +69,38 @@ class Base3DDetector(BaseDetector):
             result (dict): Prediction results.
             out_dir (str): Output directory of visualization result.
         """
+        if isinstance(data['points'][0], DC):
             points = data['points'][0]._data[0][0].numpy()
+        elif mmcv.is_list_of(data['points'][0], torch.Tensor):
+            points = data['points'][0][0]
+        else:
+            ValueError(f"Unsupported data type {type(data['points'][0])} "
+                       f'for visualization!')
+        if isinstance(data['img_metas'][0], DC):
             pts_filename = data['img_metas'][0]._data[0][0]['pts_filename']
+            box_mode_3d = data['img_metas'][0]._data[0][0]['box_mode_3d']
+        elif mmcv.is_list_of(data['img_metas'][0], dict):
+            pts_filename = data['img_metas'][0][0]['pts_filename']
+            box_mode_3d = data['img_metas'][0][0]['box_mode_3d']
+        else:
+            ValueError(f"Unsupported data type {type(data['img_metas'][0])} "
+                       f'for visualization!')
         file_name = osp.split(pts_filename)[-1].split('.')[0]
 
         assert out_dir is not None, 'Expect out_dir, got none.'
 
         pred_bboxes = copy.deepcopy(result['boxes_3d'].tensor.numpy())
         # for now we convert points into depth mode
-        if data['img_metas'][0]._data[0][0]['box_mode_3d'] != Box3DMode.DEPTH:
+        if box_mode_3d == Box3DMode.DEPTH:
+            pred_bboxes[..., 2] += pred_bboxes[..., 5] / 2
+        elif box_mode_3d == Box3DMode.CAM or box_mode_3d == Box3DMode.LIDAR:
             points = points[..., [1, 0, 2]]
             points[..., 0] *= -1
-            pred_bboxes = Box3DMode.convert(
-                pred_bboxes, data['img_metas'][0]._data[0][0]['box_mode_3d'],
+            pred_bboxes = Box3DMode.convert(pred_bboxes, box_mode_3d,
                                             Box3DMode.DEPTH)
             pred_bboxes[..., 2] += pred_bboxes[..., 5] / 2
         else:
-            pred_bboxes[..., 2] += pred_bboxes[..., 5] / 2
+            ValueError(
+                f'Unsupported box_mode_3d {box_mode_3d} for convertion!')
+
         show_result(points, None, pred_bboxes, out_dir, file_name)

mmdet3d/models/detectors/mvx_two_stage.py

+import mmcv
 import torch
+from mmcv.parallel import DataContainer as DC
 from os import path as osp
 from torch import nn as nn
 from torch.nn import functional as F
@@ -450,21 +452,37 @@ class MVXTwoStageDetector(Base3DDetector):
             result (dict): Prediction results.
             out_dir (str): Output directory of visualization result.
         """
+        if isinstance(data['points'][0], DC):
             points = data['points'][0]._data[0][0].numpy()
+        elif mmcv.is_list_of(data['points'][0], torch.Tensor):
+            points = data['points'][0][0]
+        else:
+            ValueError(f"Unsupported data type {type(data['points'][0])} "
+                       f'for visualization!')
+        if isinstance(data['img_metas'][0], DC):
             pts_filename = data['img_metas'][0]._data[0][0]['pts_filename']
+            box_mode_3d = data['img_metas'][0]._data[0][0]['box_mode_3d']
+        elif mmcv.is_list_of(data['img_metas'][0], dict):
+            pts_filename = data['img_metas'][0][0]['pts_filename']
+            box_mode_3d = data['img_metas'][0][0]['box_mode_3d']
+        else:
+            ValueError(f"Unsupported data type {type(data['img_metas'][0])} "
+                       f'for visualization!')
         file_name = osp.split(pts_filename)[-1].split('.')[0]
 
         assert out_dir is not None, 'Expect out_dir, got none.'
         inds = result['pts_bbox']['scores_3d'] > 0.1
         pred_bboxes = result['pts_bbox']['boxes_3d'][inds].tensor.numpy()
         # for now we convert points into depth mode
-        if data['img_metas'][0]._data[0][0]['box_mode_3d'] != Box3DMode.DEPTH:
+        if box_mode_3d == Box3DMode.DEPTH:
+            pred_bboxes[..., 2] += pred_bboxes[..., 5] / 2
+        elif box_mode_3d == Box3DMode.CAM or box_mode_3d == Box3DMode.LIDAR:
             points = points[..., [1, 0, 2]]
             points[..., 0] *= -1
-            pred_bboxes = Box3DMode.convert(
-                pred_bboxes, data['img_metas'][0]._data[0][0]['box_mode_3d'],
+            pred_bboxes = Box3DMode.convert(pred_bboxes, box_mode_3d,
                                             Box3DMode.DEPTH)
             pred_bboxes[..., 2] += pred_bboxes[..., 5] / 2
         else:
-            pred_bboxes[..., 2] += pred_bboxes[..., 5] / 2
+            ValueError(
+                f'Unsupported box_mode_3d {box_mode_3d} for convertion!')
         show_result(points, None, pred_bboxes, out_dir, file_name)