[Refactor] Refactor FCAF3D

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

@@ -8,7 +8,7 @@
              '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_/models/fcaf3d.py

@@ -0,0 +1,20 @@
+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/fcaf3d/fcaf3d_8xb2_scannet-3d-18class.py

@@ -0,0 +1,91 @@
+_base_ = [
+    '../_base_/models/fcaf3d.py', '../_base_/default_runtime.py',
+    '../_base_/datasets/scannet-3d.py'
+]
+n_points = 100000
+
+train_pipeline = [
+    dict(
+        type='LoadPointsFromFile',
+        coord_type='DEPTH',
+        shift_height=False,
+        use_color=True,
+        load_dim=6,
+        use_dim=[0, 1, 2, 3, 4, 5]),
+    dict(type='LoadAnnotations3D'),
+    dict(type='GlobalAlignment', rotation_axis=2),
+    dict(type='PointSample', num_points=n_points),
+    dict(
+        type='RandomFlip3D',
+        sync_2d=False,
+        flip_ratio_bev_horizontal=0.5,
+        flip_ratio_bev_vertical=0.5),
+    dict(
+        type='GlobalRotScaleTrans',
+        rot_range=[-0.087266, 0.087266],
+        scale_ratio_range=[.9, 1.1],
+        translation_std=[.1, .1, .1],
+        shift_height=False),
+    dict(type='NormalizePointsColor', color_mean=None),
+    dict(
+        type='Pack3DDetInputs',
+        keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
+]
+test_pipeline = [
+    dict(
+        type='LoadPointsFromFile',
+        coord_type='DEPTH',
+        shift_height=False,
+        use_color=True,
+        load_dim=6,
+        use_dim=[0, 1, 2, 3, 4, 5]),
+    dict(type='GlobalAlignment', rotation_axis=2),
+    dict(
+        type='MultiScaleFlipAug3D',
+        img_scale=(1333, 800),
+        pts_scale_ratio=1,
+        flip=False,
+        transforms=[
+            dict(
+                type='GlobalRotScaleTrans',
+                rot_range=[0, 0],
+                scale_ratio_range=[1., 1.],
+                translation_std=[0, 0, 0]),
+            dict(
+                type='RandomFlip3D',
+                sync_2d=False,
+                flip_ratio_bev_horizontal=0.5,
+                flip_ratio_bev_vertical=0.5),
+            dict(type='PointSample', num_points=n_points),
+            dict(type='NormalizePointsColor', color_mean=None),
+        ]),
+    dict(type='Pack3DDetInputs', keys=['points'])
+]
+train_dataloader = dict(
+    dataset=dict(
+        type='RepeatDataset',
+        times=10,
+        dataset=dict(pipeline=train_pipeline, filter_empty_gt=True)))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='AdamW', lr=0.001, weight_decay=0.0001),
+    clip_grad=dict(max_norm=10, norm_type=2))
+
+# learning rate
+param_scheduler = dict(
+    type='MultiStepLR',
+    begin=0,
+    end=12,
+    by_epoch=True,
+    milestones=[8, 11],
+    gamma=0.1)
+
+custom_hooks = [dict(type='EmptyCacheHook', after_iter=True)]
+
+# training schedule for 1x
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=12)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')

configs/fcaf3d/fcaf3d_8xb2_sunrgbd-3d-10class.py

@@ -0,0 +1,89 @@
+_base_ = [
+    '../_base_/models/fcaf3d.py', '../_base_/default_runtime.py',
+    '../_base_/datasets/sunrgbd-3d.py'
+]
+n_points = 100000
+
+model = dict(
+    bbox_head=dict(
+        num_classes=10,
+        num_reg_outs=8,
+        bbox_loss=dict(type='RotatedIoU3DLoss')))
+
+train_pipeline = [
+    dict(
+        type='LoadPointsFromFile',
+        coord_type='DEPTH',
+        shift_height=False,
+        load_dim=6,
+        use_dim=[0, 1, 2, 3, 4, 5]),
+    dict(type='LoadAnnotations3D'),
+    dict(type='PointSample', num_points=n_points),
+    dict(type='RandomFlip3D', sync_2d=False, flip_ratio_bev_horizontal=0.5),
+    dict(
+        type='GlobalRotScaleTrans',
+        rot_range=[-0.523599, 0.523599],
+        scale_ratio_range=[0.85, 1.15],
+        translation_std=[.1, .1, .1],
+        shift_height=False),
+    dict(
+        type='Pack3DDetInputs',
+        keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
+]
+test_pipeline = [
+    dict(
+        type='LoadPointsFromFile',
+        coord_type='DEPTH',
+        shift_height=False,
+        load_dim=6,
+        use_dim=[0, 1, 2, 3, 4, 5]),
+    dict(
+        type='MultiScaleFlipAug3D',
+        img_scale=(1333, 800),
+        pts_scale_ratio=1,
+        flip=False,
+        transforms=[
+            dict(
+                type='GlobalRotScaleTrans',
+                rot_range=[0, 0],
+                scale_ratio_range=[1., 1.],
+                translation_std=[0, 0, 0]),
+            dict(
+                type='RandomFlip3D',
+                sync_2d=False,
+                flip_ratio_bev_horizontal=0.5,
+                flip_ratio_bev_vertical=0.5),
+            dict(type='PointSample', num_points=n_points)
+        ]),
+    dict(type='Pack3DDetInputs', keys=['points'])
+]
+
+train_dataloader = dict(
+    batch_size=8,
+    dataset=dict(
+        type='RepeatDataset',
+        times=3,
+        dataset=dict(pipeline=train_pipeline, filter_empty_gt=True)))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='AdamW', lr=0.001, weight_decay=0.0001),
+    clip_grad=dict(max_norm=10, norm_type=2))
+
+# learning rate
+param_scheduler = dict(
+    type='MultiStepLR',
+    begin=0,
+    end=12,
+    by_epoch=True,
+    milestones=[8, 11],
+    gamma=0.1)
+
+custom_hooks = [dict(type='EmptyCacheHook', after_iter=True)]
+
+# training schedule for 1x
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=12)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')

mmdet3d/evaluation/metrics/indoor_metric.py

@@ -78,8 +78,9 @@ def compute_metrics(self, results: list) -> Dict[str, float]:
             ann_infos.append(eval_ann)
             pred_results.append(sinlge_pred_results)
 
+        # some checkpoints may not record the key "box_type_3d"
         box_type_3d, box_mode_3d = get_box_type(
-            self.dataset_meta['box_type_3d'])
+            self.dataset_meta.get('box_type_3d', 'depth'))
 
         ret_dict = indoor_eval(
             ann_infos,

mmdet3d/models/backbones/mink_resnet.py

@@ -58,7 +58,7 @@ def __init__(self, depth, in_channels, num_stages=4, pool=True):
 
         for i, num_blocks in enumerate(stage_blocks):
             setattr(
-                self, f'layer{i}',
+                self, f'layer{i + 1}',
                 self._make_layer(block, 64 * 2**i, stage_blocks[i], stride=2))
 
     def init_weights(self):
@@ -111,6 +111,6 @@ def forward(self, x):
             x = self.maxpool(x)
         outs = []
         for i in range(self.num_stages):
-            x = getattr(self, f'layer{i}')(x)
+            x = getattr(self, f'layer{i + 1}')(x)
             outs.append(x)
         return outs

mmdet3d/models/dense_heads/__init__.py

@@ -5,6 +5,7 @@
 from .base_conv_bbox_head import BaseConvBboxHead
 from .base_mono3d_dense_head import BaseMono3DDenseHead
 from .centerpoint_head import CenterHead
+from .fcaf3d_head import FCAF3DHead
 from .fcos_mono3d_head import FCOSMono3DHead
 from .free_anchor3d_head import FreeAnchor3DHead
 from .groupfree3d_head import GroupFree3DHead
@@ -22,5 +23,5 @@
     'SSD3DHead', 'BaseConvBboxHead', 'CenterHead', 'ShapeAwareHead',
     'BaseMono3DDenseHead', 'AnchorFreeMono3DHead', 'FCOSMono3DHead',
     'GroupFree3DHead', 'PointRPNHead', 'SMOKEMono3DHead', 'PGDHead',
-    'MonoFlexHead', 'Base3DDenseHead'
+    'MonoFlexHead', 'Base3DDenseHead', 'FCAF3DHead'
 ]