Bump version to v1.1.0rc2

Bump to v1.1.0rc2

configs/_base_/datasets/scannet-3d.py

@@ -3,12 +3,12 @@ dataset_type = 'ScanNetDataset'
 data_root = 'data/scannet/'
 
 metainfo = dict(
-    CLASSES=('cabinet', 'bed', 'chair', 'sofa', 'table', 'door', 'window',
+    classes=('cabinet', 'bed', 'chair', 'sofa', 'table', 'door', 'window',
              'bookshelf', 'picture', 'counter', 'desk', 'curtain',
              'refrigerator', 'showercurtrain', 'toilet', 'sink', 'bathtub',
              'garbagebin'))
 
-file_client_args = dict(backend='disk')
+# file_client_args = dict(backend='disk')
 # Uncomment the following if use ceph or other file clients.
 # See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
 # for more details.

configs/_base_/datasets/scannet-seg.py

@@ -3,7 +3,7 @@ class_names = ('wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table',
                'door', 'window', 'bookshelf', 'picture', 'counter', 'desk',
                'curtain', 'refrigerator', 'showercurtrain', 'toilet', 'sink',
                'bathtub', 'otherfurniture')
-metainfo = dict(CLASSES=class_names)
+metainfo = dict(classes=class_names)
 dataset_type = 'ScanNetSegDataset'
 data_root = 'data/scannet/'
 input_modality = dict(use_lidar=True, use_camera=False)

configs/_base_/datasets/sunrgbd-3d.py

@@ -3,7 +3,7 @@ data_root = 'data/sunrgbd/'
 class_names = ('bed', 'table', 'sofa', 'chair', 'toilet', 'desk', 'dresser',
                'night_stand', 'bookshelf', 'bathtub')
 
-metainfo = dict(CLASSES=class_names)
+metainfo = dict(classes=class_names)
 
 file_client_args = dict(backend='disk')
 # Uncomment the following if use ceph or other file clients.

configs/_base_/datasets/waymoD5-3d-3class.py

@@ -16,7 +16,7 @@ file_client_args = dict(backend='disk')
 #     })
 
 class_names = ['Car', 'Pedestrian', 'Cyclist']
-metainfo = dict(CLASSES=class_names)
+metainfo = dict(classes=class_names)
 
 point_cloud_range = [-74.88, -74.88, -2, 74.88, 74.88, 4]
 input_modality = dict(use_lidar=True, use_camera=False)
@@ -151,7 +151,8 @@ val_evaluator = dict(
     ann_file='./data/waymo/kitti_format/waymo_infos_val.pkl',
     waymo_bin_file='./data/waymo/waymo_format/gt.bin',
     data_root='./data/waymo/waymo_format',
-    file_client_args=file_client_args)
+    file_client_args=file_client_args,
+    convert_kitti_format=False)
 test_evaluator = val_evaluator
 
 vis_backends = [dict(type='LocalVisBackend')]

configs/_base_/datasets/waymoD5-3d-car.py

@@ -11,7 +11,7 @@ file_client_args = dict(backend='disk')
 #     backend='petrel', path_mapping=dict(data='s3://waymo_data/'))
 
 class_names = ['Car']
-metainfo = dict(CLASSES=class_names)
+metainfo = dict(classes=class_names)
 
 point_cloud_range = [-74.88, -74.88, -2, 74.88, 74.88, 4]
 input_modality = dict(use_lidar=True, use_camera=False)
@@ -135,7 +135,8 @@ val_evaluator = dict(
     type='WaymoMetric',
     ann_file='./data/waymo/kitti_format/waymo_infos_val.pkl',
     waymo_bin_file='./data/waymo/waymo_format/gt.bin',
-    data_root='./data/waymo/waymo_format')
+    data_root='./data/waymo/waymo_format',
+    convert_kitti_format=False)
 test_evaluator = val_evaluator
 
 vis_backends = [dict(type='LocalVisBackend')]

configs/_base_/datasets/waymoD5-fov-mono3d-3class.py

+# dataset settings
+# D3 in the config name means the whole dataset is divided into 3 folds
+# We only use one fold for efficient experiments
+dataset_type = 'WaymoDataset'
+data_root = 'data/waymo/kitti_format/'
+class_names = ['Car', 'Pedestrian', 'Cyclist']
+input_modality = dict(use_lidar=False, use_camera=True)
+file_client_args = dict(backend='disk')
+# Uncomment the following if use ceph or other file clients.
+# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
+# for more details.
+train_pipeline = [
+    dict(type='LoadImageFromFileMono3D'),
+    dict(
+        type='LoadAnnotations3D',
+        with_bbox=True,
+        with_label=True,
+        with_attr_label=False,
+        with_bbox_3d=True,
+        with_label_3d=True,
+        with_bbox_depth=True),
+    # base shape (1248, 832), scale (0.95, 1.05)
+    dict(
+        type='RandomResize3D',
+        scale=(1284, 832),
+        ratio_range=(0.95, 1.05),
+        keep_ratio=True,
+    ),
+    dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
+    dict(
+        type='Pack3DDetInputs',
+        keys=[
+            'img', 'gt_bboxes', 'gt_bboxes_labels', 'gt_bboxes_3d',
+            'gt_labels_3d', 'centers_2d', 'depths'
+        ]),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFileMono3D'),
+    dict(
+        type='RandomResize3D',
+        scale=(1248, 832),
+        ratio_range=(1., 1.),
+        keep_ratio=True),
+    dict(type='Pack3DDetInputs', keys=['img']),
+]
+# construct a pipeline for data and gt loading in show function
+# please keep its loading function consistent with test_pipeline (e.g. client)
+eval_pipeline = [
+    dict(type='LoadImageFromFileMono3D'),
+    dict(
+        type='RandomResize3D',
+        scale=(1248, 832),
+        ratio_range=(1., 1.),
+        keep_ratio=True),
+    dict(type='Pack3DDetInputs', keys=['img']),
+]
+
+metainfo = dict(CLASSES=class_names)
+
+train_dataloader = dict(
+    batch_size=3,
+    num_workers=3,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='waymo_infos_train.pkl',
+        data_prefix=dict(
+            pts='training/velodyne',
+            CAM_FRONT='training/image_0',
+            CAM_FRONT_RIGHT='training/image_1',
+            CAM_FRONT_LEFT='training/image_2',
+            CAM_SIDE_RIGHT='training/image_3',
+            CAM_SIDE_LEFT='training/image_4'),
+        pipeline=train_pipeline,
+        modality=input_modality,
+        test_mode=False,
+        metainfo=metainfo,
+        # we use box_type_3d='LiDAR' in kitti and nuscenes dataset
+        # and box_type_3d='Depth' in sunrgbd and scannet dataset.
+        box_type_3d='Camera',
+        load_type='fov_image_based',
+        # load one frame every three frames
+        load_interval=5))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=1,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            pts='training/velodyne',
+            CAM_FRONT='training/image_0',
+            CAM_FRONT_RIGHT='training/image_1',
+            CAM_FRONT_LEFT='training/image_2',
+            CAM_SIDE_RIGHT='training/image_3',
+            CAM_SIDE_LEFT='training/image_4'),
+        ann_file='waymo_infos_val.pkl',
+        pipeline=eval_pipeline,
+        modality=input_modality,
+        test_mode=True,
+        metainfo=metainfo,
+        # we use box_type_3d='LiDAR' in kitti and nuscenes dataset
+        # and box_type_3d='Depth' in sunrgbd and scannet dataset.
+        box_type_3d='Camera',
+        load_type='fov_image_based',
+    ))
+
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=1,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        data_prefix=dict(
+            pts='training/velodyne',
+            CAM_FRONT='training/image_0',
+            CAM_FRONT_RIGHT='training/image_1',
+            CAM_FRONT_LEFT='training/image_2',
+            CAM_SIDE_RIGHT='training/image_3',
+            CAM_SIDE_LEFT='training/image_4'),
+        ann_file='waymo_infos_val.pkl',
+        pipeline=eval_pipeline,
+        modality=input_modality,
+        test_mode=True,
+        metainfo=metainfo,
+        # we use box_type_3d='LiDAR' in kitti and nuscenes dataset
+        # and box_type_3d='Depth' in sunrgbd and scannet dataset.
+        box_type_3d='Camera',
+        load_type='fov_image_based',
+    ))
+
+val_evaluator = dict(
+    type='WaymoMetric',
+    ann_file='./data/waymo/kitti_format/waymo_infos_val.pkl',
+    waymo_bin_file='./data/waymo/waymo_format/fov_gt.bin',
+    data_root='./data/waymo/waymo_format',
+    metric='LET_mAP',
+    load_type='fov_image_based',
+)
+test_evaluator = val_evaluator

configs/_base_/datasets/waymoD5-mono3d-3class.py → configs/_base_/datasets/waymoD5-mv-mono3d-3class.py

@@ -56,7 +56,7 @@ eval_pipeline = [
     dict(type='Pack3DDetInputs', keys=['img']),
 ]
 
-metainfo = dict(CLASSES=class_names)
+metainfo = dict(classes=class_names)
 
 train_dataloader = dict(
     batch_size=3,
@@ -81,7 +81,7 @@ train_dataloader = dict(
         # we use box_type_3d='LiDAR' in kitti and nuscenes dataset
         # and box_type_3d='Depth' in sunrgbd and scannet dataset.
         box_type_3d='Camera',
-        task='mono3d',
+        load_type='mv_image_based',
         # load one frame every three frames
         load_interval=5))
 
@@ -109,7 +109,7 @@ val_dataloader = dict(
         # we use box_type_3d='LiDAR' in kitti and nuscenes dataset
         # and box_type_3d='Depth' in sunrgbd and scannet dataset.
         box_type_3d='Camera',
-        task='mono3d',
+        load_type='mv_image_based',
     ))
 
 test_dataloader = dict(
@@ -136,7 +136,7 @@ test_dataloader = dict(
         # we use box_type_3d='LiDAR' in kitti and nuscenes dataset
         # and box_type_3d='Depth' in sunrgbd and scannet dataset.
         box_type_3d='Camera',
-        task='mono3d',
+        load_type='mv_image_based',
     ))
 
 val_evaluator = dict(
@@ -145,5 +145,6 @@ val_evaluator = dict(
     waymo_bin_file='./data/waymo/waymo_format/cam_gt.bin',
     data_root='./data/waymo/waymo_format',
     metric='LET_mAP',
-    task='mono3d')
+    load_type='mv_image_based',
+)
 test_evaluator = val_evaluator

configs/_base_/datasets/waymoD5-mv3d-3class.py

@@ -62,7 +62,7 @@ eval_pipeline = [
     dict(type='MultiViewWrapper', transforms=test_transforms),
     dict(type='Pack3DDetInputs', keys=['img'])
 ]
-metainfo = dict(CLASSES=class_names)
+metainfo = dict(classes=class_names)
 
 train_dataloader = dict(
     batch_size=2,

configs/_base_/models/cascade-mask-rcnn_r50_fpn.py

@@ -2,6 +2,7 @@
 model = dict(
     type='CascadeRCNN',
     pretrained='torchvision://resnet50',
+    _scope_='mmdet',
     backbone=dict(
         type='ResNet',
         depth=50,

configs/_base_/models/fcaf3d.py

+model = dict(
+    type='MinkSingleStage3DDetector',
+    data_preprocessor=dict(type='Det3DDataPreprocessor'),
+    backbone=dict(type='MinkResNet', in_channels=3, depth=34),
+    bbox_head=dict(
+        type='FCAF3DHead',
+        in_channels=(64, 128, 256, 512),
+        out_channels=128,
+        voxel_size=.01,
+        pts_prune_threshold=100000,
+        pts_assign_threshold=27,
+        pts_center_threshold=18,
+        num_classes=18,
+        num_reg_outs=6,
+        center_loss=dict(type='mmdet.CrossEntropyLoss', use_sigmoid=True),
+        bbox_loss=dict(type='AxisAlignedIoULoss'),
+        cls_loss=dict(type='mmdet.FocalLoss'),
+    ),
+    train_cfg=dict(),
+    test_cfg=dict(nms_pre=1000, iou_thr=.5, score_thr=.01))

configs/_base_/models/imvotenet.py

@@ -63,9 +63,9 @@ model = dict(
 
     # model training and testing settings
     train_cfg=dict(
+        _scope_='mmdet',
         img_rpn=dict(
             assigner=dict(
-                _scope_='mmdet',
                 type='MaxIoUAssigner',
                 pos_iou_thr=0.7,
                 neg_iou_thr=0.3,
@@ -73,7 +73,7 @@ model = dict(
                 match_low_quality=True,
                 ignore_iof_thr=-1),
             sampler=dict(
-                type='mmdet.RandomSampler',
+                type='RandomSampler',
                 num=256,
                 pos_fraction=0.5,
                 neg_pos_ub=-1,
@@ -90,7 +90,6 @@ model = dict(
             min_bbox_size=0),
         img_rcnn=dict(
             assigner=dict(
-                _scope_='mmdet',
                 type='MaxIoUAssigner',
                 pos_iou_thr=0.5,
                 neg_iou_thr=0.5,
@@ -98,7 +97,7 @@ model = dict(
                 match_low_quality=False,
                 ignore_iof_thr=-1),
             sampler=dict(
-                type='mmdet.RandomSampler',
+                type='RandomSampler',
                 num=512,
                 pos_fraction=0.25,
                 neg_pos_ub=-1,

configs/_base_/models/mask-rcnn_r50_fpn.py

@@ -2,6 +2,7 @@
 model = dict(
     type='MaskRCNN',
     pretrained='torchvision://resnet50',
+    _scope_='mmdet',
     backbone=dict(
         type='ResNet',
         depth=50,

configs/_base_/schedules/seg-cosine-100e.py

@@ -16,8 +16,8 @@ param_scheduler = [
 ]
 
 # runtime settings
-train_cfg = dict(by_epoch=True, max_epochs=100)
-val_cfg = dict(interval=1)
+train_cfg = dict(by_epoch=True, max_epochs=100, val_interval=1)
+val_cfg = dict()
 test_cfg = dict()
 
 # Default setting for scaling LR automatically

configs/_base_/schedules/seg-cosine-150e.py

@@ -16,8 +16,8 @@ param_scheduler = [
 ]
 
 # runtime settings
-train_cfg = dict(by_epoch=True, max_epochs=150)
-val_cfg = dict(interval=1)
+train_cfg = dict(by_epoch=True, max_epochs=150, val_interval=1)
+val_cfg = dict()
 test_cfg = dict()
 
 # Default setting for scaling LR automatically

configs/_base_/schedules/seg-cosine-200e.py

@@ -16,8 +16,8 @@ param_scheduler = [
 ]
 
 # runtime settings
-train_cfg = dict(by_epoch=True, max_epochs=200)
-val_cfg = dict(interval=1)
+train_cfg = dict(by_epoch=True, max_epochs=200, val_interval=1)
+val_cfg = dict()
 test_cfg = dict()
 
 # Default setting for scaling LR automatically

configs/_base_/schedules/seg-cosine-50e.py

@@ -16,8 +16,8 @@ param_scheduler = [
 ]
 
 # runtime settings
-train_cfg = dict(by_epoch=True, max_epochs=50)
-val_cfg = dict(interval=1)
+train_cfg = dict(by_epoch=True, max_epochs=50, val_interval=1)
+val_cfg = dict()
 test_cfg = dict()
 
 # Default setting for scaling LR automatically

configs/benchmark/hv_PartA2_secfpn_4x8_cyclic_80e_pcdet_kitti-3d-3class.py

@@ -210,7 +210,7 @@ model = dict(
 dataset_type = 'KittiDataset'
 data_root = 'data/kitti/'
 class_names = ['Pedestrian', 'Cyclist', 'Car']
-metainfo = dict(CLASSES=class_names)
+metainfo = dict(classes=class_names)
 input_modality = dict(use_lidar=True, use_camera=False)
 db_sampler = dict(
     data_root=data_root,

configs/benchmark/hv_pointpillars_secfpn_3x8_100e_det3d_kitti-3d-car.py

@@ -81,7 +81,7 @@ model = dict(
 dataset_type = 'KittiDataset'
 data_root = 'data/kitti/'
 class_names = ['Car']
-metainfo = dict(CLASSES=class_names)
+metainfo = dict(classes=class_names)
 input_modality = dict(use_lidar=True, use_camera=False)
 db_sampler = dict(
     data_root=data_root,

configs/benchmark/hv_pointpillars_secfpn_4x8_80e_pcdet_kitti-3d-3class.py

@@ -107,7 +107,7 @@ model = dict(
 dataset_type = 'KittiDataset'
 data_root = 'data/kitti/'
 class_names = ['Pedestrian', 'Cyclist', 'Car']
-metainfo = dict(CLASSES=class_names)
+metainfo = dict(classes=class_names)
 
 input_modality = dict(use_lidar=True, use_camera=False)
 db_sampler = dict(

configs/benchmark/hv_second_secfpn_4x8_80e_pcdet_kitti-3d-3class.py

@@ -99,7 +99,7 @@ model = dict(
 dataset_type = 'KittiDataset'
 data_root = 'data/kitti/'
 class_names = ['Pedestrian', 'Cyclist', 'Car']
-metainfo = dict(CLASSES=class_names)
+metainfo = dict(classes=class_names)
 input_modality = dict(use_lidar=True, use_camera=False)
 db_sampler = dict(
     data_root=data_root,