[Fix] Fix PartA2 bug (#1538)

* [Fix] fixed compatibility of MMCV (#1508)

* fixed GPG key error

* fixed compatibility of MMCV

* fix parta2 bug
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
Co-authored-by: atinfinity <dandelion1124@gmail.com>

configs/parta2/hv_PartA2_secfpn_2x8_cyclic_80e_kitti-3d-3class.py

@@ -90,6 +90,7 @@ data = dict(
             pipeline=train_pipeline,
             modality=input_modality,
             classes=class_names,
+            box_type_3d='LiDAR',
             test_mode=False)),
     val=dict(
         type=dataset_type,
@@ -100,6 +101,7 @@ data = dict(
         pipeline=test_pipeline,
         modality=input_modality,
         classes=class_names,
+        box_type_3d='LiDAR',
         test_mode=True),
     test=dict(
         type=dataset_type,
@@ -110,6 +112,7 @@ data = dict(
         pipeline=test_pipeline,
         modality=input_modality,
         classes=class_names,
+        box_type_3d='LiDAR',
         test_mode=True))
 
 # Part-A2 uses a different learning rate from what SECOND uses.

mmdet3d/models/detectors/two_stage.py

@@ -30,7 +30,8 @@ class TwoStage3DDetector(Base3DDetector, TwoStageDetector):
                           'please use "init_cfg" instead')
             backbone.pretrained = pretrained
         self.backbone = build_backbone(backbone)
-
+        self.train_cfg = train_cfg
+        self.test_cfg = test_cfg
         if neck is not None:
             self.neck = build_neck(neck)
 

mmdet3d/models/middle_encoders/sparse_unet.py

@@ -11,6 +11,7 @@ else:
 from mmcv.runner import BaseModule, auto_fp16
 
 from mmdet3d.ops import SparseBasicBlock, make_sparse_convmodule
+from mmdet3d.ops.sparse_block import replace_feature
 from ..builder import MIDDLE_ENCODERS
 
 
@@ -168,10 +169,11 @@ class SparseUNet(BaseModule):
             :obj:`SparseConvTensor`: Upsampled feature.
         """
         x = lateral_layer(x_lateral)
-        x.features = torch.cat((x_bottom.features, x.features), dim=1)
+        x = replace_feature(x, torch.cat((x_bottom.features, x.features),
+                                         dim=1))
         x_merge = merge_layer(x)
         x = self.reduce_channel(x, x_merge.features.shape[1])
-        x.features = x_merge.features + x.features
+        x = replace_feature(x, x_merge.features + x.features)
         x = upsample_layer(x)
         return x
 
@@ -191,8 +193,7 @@ class SparseUNet(BaseModule):
         n, in_channels = features.shape
         assert (in_channels % out_channels
                 == 0) and (in_channels >= out_channels)
-
-        x.features = features.view(n, out_channels, -1).sum(dim=2)
+        x = replace_feature(x, features.view(n, out_channels, -1).sum(dim=2))
         return x
 
     def make_encoder_layers(self, make_block, norm_cfg, in_channels):

mmdet3d/models/roi_heads/bbox_heads/parta2_bbox_head.py

@@ -2,7 +2,15 @@
 import numpy as np
 import torch
 from mmcv.cnn import ConvModule, normal_init
-from mmcv.ops import SparseConvTensor, SparseMaxPool3d, SparseSequential
+
+from mmdet3d.ops.spconv import IS_SPCONV2_AVAILABLE
+
+if IS_SPCONV2_AVAILABLE:
+    from spconv.pytorch import (SparseConvTensor, SparseMaxPool3d,
+                                SparseSequential)
+else:
+    from mmcv.ops import SparseConvTensor, SparseMaxPool3d, SparseSequential
+
 from mmcv.runner import BaseModule
 from torch import nn as nn
 
@@ -252,7 +260,7 @@ class PartA2BboxHead(BaseModule):
                                    sparse_idx[:, 2], sparse_idx[:, 3]]
         seg_features = seg_feats[sparse_idx[:, 0], sparse_idx[:, 1],
                                  sparse_idx[:, 2], sparse_idx[:, 3]]
-        coords = sparse_idx.int()
+        coords = sparse_idx.int().contiguous()
         part_features = SparseConvTensor(part_features, coords, sparse_shape,
                                          rcnn_batch_size)
         seg_features = SparseConvTensor(seg_features, coords, sparse_shape,