Merge branch 'main_tmp' into indoor_pipeline

.gitlab-ci.yml

@@ -16,7 +16,7 @@ before_script:
 .linting_template: &linting_template_def
   stage: linting
   script:
-    - pip install flake8 yapf isort
+    - pip install flake8==3.7.9 yapf isort
     - flake8 .
     - isort -rc --check-only --diff mmdet3d/ tools/ tests/
     - yapf -r -d mmdet3d/ tools/ tests/ configs/
@@ -26,6 +26,7 @@ before_script:
   script:
     - echo "Start building..."
     - pip install "git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI"
+    - pip install git+https://github.com/open-mmlab/mmcv.git
     - pip install git+https://github.com/open-mmlab/mmdetection.git
     - python -c "import mmdet; print(mmdet.__version__)"
     - pip install -v -e .[all]

configs/kitti/dv_mvx-v2_second_secfpn_fpn-fusion_adamw_2x8_80e_kitti-3d-3class.py

@@ -57,13 +57,13 @@ model = dict(
         in_channels=256,
         layer_nums=[5, 5],
         layer_strides=[1, 2],
-        num_filters=[128, 256],
+        out_channels=[128, 256],
     ),
     pts_neck=dict(
         type='SECONDFPN',
         in_channels=[128, 256],
         upsample_strides=[1, 2],
-        num_upsample_filters=[256, 256],
+        out_channels=[256, 256],
     ),
     pts_bbox_head=dict(
         type='SECONDHead',

configs/kitti/dv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py

@@ -28,13 +28,13 @@ model = dict(
         in_channels=64,
         layer_nums=[3, 5, 5],
         layer_strides=[2, 2, 2],
-        num_filters=[64, 128, 256],
+        out_channels=[64, 128, 256],
     ),
     neck=dict(
         type='SECONDFPN',
         in_channels=[64, 128, 256],
         upsample_strides=[1, 2, 4],
-        num_upsample_filters=[128, 128, 128],
+        out_channels=[128, 128, 128],
     ),
     bbox_head=dict(
         type='SECONDHead',

configs/kitti/dv_second_secfpn_2x8_cosine_80e_kitti-3d-3class.py

@@ -26,13 +26,13 @@ model = dict(
         in_channels=256,
         layer_nums=[5, 5],
         layer_strides=[1, 2],
-        num_filters=[128, 256],
+        out_channels=[128, 256],
     ),
     neck=dict(
         type='SECONDFPN',
         in_channels=[128, 256],
         upsample_strides=[1, 2],
-        num_upsample_filters=[256, 256],
+        out_channels=[256, 256],
     ),
     bbox_head=dict(
         type='SECONDHead',

configs/kitti/dv_second_secfpn_6x8_80e_kitti-3d-car.py

@@ -26,13 +26,13 @@ model = dict(
         in_channels=256,
         layer_nums=[5, 5],
         layer_strides=[1, 2],
-        num_filters=[128, 256],
+        out_channels=[128, 256],
     ),
     neck=dict(
         type='SECONDFPN',
         in_channels=[128, 256],
         upsample_strides=[1, 2],
-        num_upsample_filters=[256, 256],
+        out_channels=[256, 256],
     ),
     bbox_head=dict(
         type='SECONDHead',

configs/kitti/hv_PartA2_secfpn_4x8_cosine_80e_kitti-3d-3class.py

@@ -22,12 +22,12 @@ model = dict(
         in_channels=256,
         layer_nums=[5, 5],
         layer_strides=[1, 2],
-        num_filters=[128, 256]),
+        out_channels=[128, 256]),
     neck=dict(
         type='SECONDFPN',
         in_channels=[128, 256],
         upsample_strides=[1, 2],
-        num_upsample_filters=[256, 256]),
+        out_channels=[256, 256]),
     rpn_head=dict(
         type='PartA2RPNHead',
         class_name=['Pedestrian', 'Cyclist', 'Car'],

configs/kitti/hv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py

@@ -27,13 +27,13 @@ model = dict(
         in_channels=64,
         layer_nums=[3, 5, 5],
         layer_strides=[2, 2, 2],
-        num_filters=[64, 128, 256],
+        out_channels=[64, 128, 256],
     ),
     neck=dict(
         type='SECONDFPN',
         in_channels=[64, 128, 256],
         upsample_strides=[1, 2, 4],
-        num_upsample_filters=[128, 128, 128],
+        out_channels=[128, 128, 128],
     ),
     bbox_head=dict(
         type='SECONDHead',

configs/kitti/hv_second_secfpn_6x8_80e_kitti-3d-car.py

@@ -26,13 +26,13 @@ model = dict(
         in_channels=256,
         layer_nums=[5, 5],
         layer_strides=[1, 2],
-        num_filters=[128, 256],
+        out_channels=[128, 256],
     ),
     neck=dict(
         type='SECONDFPN',
         in_channels=[128, 256],
         upsample_strides=[1, 2],
-        num_upsample_filters=[256, 256],
+        out_channels=[256, 256],
     ),
     bbox_head=dict(
         type='SECONDHead',

configs/nus/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d.py

@@ -34,14 +34,14 @@ model = dict(
         norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
         layer_nums=[3, 5, 5],
         layer_strides=[2, 2, 2],
-        num_filters=[64, 128, 256],
+        out_channels=[64, 128, 256],
     ),
     pts_neck=dict(
         type='SECONDFPN',
         norm_cfg=dict(type='naiveSyncBN2d', eps=1e-3, momentum=0.01),
         in_channels=[64, 128, 256],
         upsample_strides=[1, 2, 4],
-        num_upsample_filters=[128, 128, 128],
+        out_channels=[128, 128, 128],
     ),
     pts_bbox_head=dict(
         type='Anchor3DVeloHead',

mmdet3d/models/backbones/second.py

-from functools import partial
-
 import torch.nn as nn
-from mmcv.cnn import build_norm_layer
+from mmcv.cnn import build_conv_layer, build_norm_layer
 from mmcv.runner import load_checkpoint
 
 from mmdet.models import BACKBONES
 
 
-class Empty(nn.Module):
-
-    def __init__(self, *args, **kwargs):
-        super(Empty, self).__init__()
-
-    def forward(self, *args, **kwargs):
-        if len(args) == 1:
-            return args[0]
-        elif len(args) == 0:
-            return None
-        return args
-
-
 @BACKBONES.register_module()
 class SECOND(nn.Module):
-    """Compare with RPN, RPNV2 support arbitrary number of stage.
+    """Backbone network for SECOND/PointPillars/PartA2/MVXNet
+
+    Args:
+        in_channels (int): Input channels
+        out_channels (list[int]): Output channels for multi-scale feature maps
+        layer_nums (list[int]): Number of layers in each stage
+        layer_strides (list[int]): Strides of each stage
+        norm_cfg (dict): Config dict of normalization layers
+        conv_cfg (dict): Config dict of convolutional layers
     """
 
     def __init__(self,
                  in_channels=128,
+                 out_channels=[128, 128, 256],
                  layer_nums=[3, 5, 5],
                  layer_strides=[2, 2, 2],
-                 num_filters=[128, 128, 256],
-                 norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01)):
+                 norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01),
+                 conv_cfg=dict(type='Conv2d', bias=False)):
         super(SECOND, self).__init__()
         assert len(layer_strides) == len(layer_nums)
-        assert len(num_filters) == len(layer_nums)
-
-        if norm_cfg is not None:
-            Conv2d = partial(nn.Conv2d, bias=False)
-        else:
-            Conv2d = partial(nn.Conv2d, bias=True)
+        assert len(out_channels) == len(layer_nums)
 
-        in_filters = [in_channels, *num_filters[:-1]]
+        in_filters = [in_channels, *out_channels[:-1]]
         # note that when stride > 1, conv2d with same padding isn't
         # equal to pad-conv2d. we should use pad-conv2d.
         blocks = []
-
         for i, layer_num in enumerate(layer_nums):
-            norm_layer = (
-                build_norm_layer(norm_cfg, num_filters[i])[1]
-                if norm_cfg is not None else Empty)
             block = [
-                nn.ZeroPad2d(1),
-                Conv2d(
-                    in_filters[i], num_filters[i], 3, stride=layer_strides[i]),
-                norm_layer,
+                build_conv_layer(
+                    conv_cfg,
+                    in_filters[i],
+                    out_channels[i],
+                    3,
+                    stride=layer_strides[i],
+                    padding=1),
+                build_norm_layer(norm_cfg, out_channels[i])[1],
                 nn.ReLU(inplace=True),
             ]
             for j in range(layer_num):
-                norm_layer = (
-                    build_norm_layer(norm_cfg, num_filters[i])[1]
-                    if norm_cfg is not None else Empty)
                 block.append(
-                    Conv2d(num_filters[i], num_filters[i], 3, padding=1))
-                block.append(norm_layer)
+                    build_conv_layer(
+                        conv_cfg,
+                        out_channels[i],
+                        out_channels[i],
+                        3,
+                        padding=1))
+                block.append(build_norm_layer(norm_cfg, out_channels[i])[1])
                 block.append(nn.ReLU(inplace=True))
 
             block = nn.Sequential(*block)
@@ -71,6 +62,8 @@ class SECOND(nn.Module):
         self.blocks = nn.ModuleList(blocks)
 
     def init_weights(self, pretrained=None):
+        # Do not initialize the conv layers
+        # to follow the original implementation
         if isinstance(pretrained, str):
             from mmdet3d.utils import get_root_logger
             logger = get_root_logger()

mmdet3d/models/necks/second_fpn.py

-from functools import partial
-
 import torch
 import torch.nn as nn
-from mmcv.cnn import build_norm_layer, constant_init, kaiming_init
-from torch.nn import Sequential
-from torch.nn.modules.batchnorm import _BatchNorm
+from mmcv.cnn import (build_norm_layer, build_upsample_layer, constant_init,
+                      is_norm, kaiming_init)
 
 from mmdet.models import NECKS
 from .. import builder
@@ -12,36 +9,40 @@ from .. import builder
 
 @NECKS.register_module()
 class SECONDFPN(nn.Module):
-    """Compare with RPN, RPNV2 support arbitrary number of stage.
+    """FPN used in SECOND/PointPillars/PartA2/MVXNet
+
+    Args:
+        in_channels (list[int]): Input channels of multi-scale feature maps
+        out_channels (list[int]): Output channels of feature maps
+        upsample_strides (list[int]): Strides used to upsample the feature maps
+        norm_cfg (dict): Config dict of normalization layers
+        upsample_cfg (dict): Config dict of upsample layers
     """
 
     def __init__(self,
-                 use_norm=True,
                  in_channels=[128, 128, 256],
+                 out_channels=[256, 256, 256],
                  upsample_strides=[1, 2, 4],
-                 num_upsample_filters=[256, 256, 256],
-                 norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01)):
+                 norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01),
+                 upsample_cfg=dict(type='deconv', bias=False)):
         # if for GroupNorm,
         # cfg is dict(type='GN', num_groups=num_groups, eps=1e-3, affine=True)
         super(SECONDFPN, self).__init__()
-        assert len(num_upsample_filters) == len(upsample_strides)
+        assert len(out_channels) == len(upsample_strides) == len(in_channels)
         self.in_channels = in_channels
-
-        ConvTranspose2d = partial(nn.ConvTranspose2d, bias=False)
+        self.out_channels = out_channels
 
         deblocks = []
-
-        for i, num_upsample_filter in enumerate(num_upsample_filters):
-            norm_layer = build_norm_layer(norm_cfg, num_upsample_filter)[1]
-            deblock = Sequential(
-                ConvTranspose2d(
-                    in_channels[i],
-                    num_upsample_filter,
-                    upsample_strides[i],
-                    stride=upsample_strides[i]),
-                norm_layer,
-                nn.ReLU(inplace=True),
-            )
+        for i, out_channel in enumerate(out_channels):
+            upsample_layer = build_upsample_layer(
+                upsample_cfg,
+                in_channels=in_channels[i],
+                out_channels=out_channel,
+                kernel_size=upsample_strides[i],
+                stride=upsample_strides[i])
+            deblock = nn.Sequential(upsample_layer,
+                                    build_norm_layer(norm_cfg, out_channel)[1],
+                                    nn.ReLU(inplace=True))
             deblocks.append(deblock)
         self.deblocks = nn.ModuleList(deblocks)
 
@@ -49,7 +50,7 @@ class SECONDFPN(nn.Module):
         for m in self.modules():
             if isinstance(m, nn.Conv2d):
                 kaiming_init(m)
-            elif isinstance(m, (_BatchNorm, nn.GroupNorm)):
+            elif is_norm(m):
                 constant_init(m, 1)
 
     def forward(self, x):
@@ -65,30 +66,34 @@ class SECONDFPN(nn.Module):
 
 @NECKS.register_module()
 class SECONDFusionFPN(SECONDFPN):
-    """Compare with RPN, RPNV2 support arbitrary number of stage.
+    """FPN used in multi-modality SECOND/PointPillars
+
+    Args:
+        in_channels (list[int]): Input channels of multi-scale feature maps
+        out_channels (list[int]): Output channels of feature maps
+        upsample_strides (list[int]): Strides used to upsample the feature maps
+        norm_cfg (dict): Config dict of normalization layers
+        upsample_cfg (dict): Config dict of upsample layers
+        downsample_rates (list[int]): The downsample rate of feature map in
+            comparison to the original voxelization input
+        fusion_layer (dict): Config dict of fusion layers
     """
 
     def __init__(self,
-                 use_norm=True,
                  in_channels=[128, 128, 256],
+                 out_channels=[256, 256, 256],
                  upsample_strides=[1, 2, 4],
-                 num_upsample_filters=[256, 256, 256],
                  norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01),
-                 down_sample_rate=[40, 8, 8],
-                 fusion_layer=None,
-                 cat_points=False):
-        super(SECONDFusionFPN, self).__init__(
-            use_norm,
-            in_channels,
-            upsample_strides,
-            num_upsample_filters,
-            norm_cfg,
-        )
+                 upsample_cfg=dict(type='deconv', bias=False),
+                 downsample_rates=[40, 8, 8],
+                 fusion_layer=None):
+        super(SECONDFusionFPN,
+              self).__init__(in_channels, out_channels, upsample_strides,
+                             norm_cfg, upsample_cfg)
         self.fusion_layer = None
         if fusion_layer is not None:
             self.fusion_layer = builder.build_fusion_layer(fusion_layer)
-        self.cat_points = cat_points
-        self.down_sample_rate = down_sample_rate
+        self.downsample_rates = downsample_rates
 
     def forward(self,
                 x,
@@ -107,11 +112,11 @@ class SECONDFusionFPN(SECONDFPN):
             downsample_pts_coors = torch.zeros_like(coors)
             downsample_pts_coors[:, 0] = coors[:, 0]
             downsample_pts_coors[:, 1] = (
-                coors[:, 1] / self.down_sample_rate[0])
+                coors[:, 1] / self.downsample_rates[0])
             downsample_pts_coors[:, 2] = (
-                coors[:, 2] / self.down_sample_rate[1])
+                coors[:, 2] / self.downsample_rates[1])
             downsample_pts_coors[:, 3] = (
-                coors[:, 3] / self.down_sample_rate[2])
+                coors[:, 3] / self.downsample_rates[2])
             # fusion for each point
             out = self.fusion_layer(img_feats, points, out,
                                     downsample_pts_coors, img_meta)

requirements/build.txt

 # These must be installed before building mmdetection
 numpy
-torch>=1.1
+torch>=1.3

requirements/runtime.txt

 matplotlib
-mmcv>=0.5.0
+mmcv>=0.5.1
 numba==0.45.1
 numpy
 # need older pillow until torchvision is fixed

tests/test_fpn.py

+import pytest
+
+
+def test_secfpn():
+    neck_cfg = dict(
+        type='SECONDFPN',
+        in_channels=[2, 3],
+        upsample_strides=[1, 2],
+        out_channels=[4, 6],
+    )
+    from mmdet.models.builder import build_neck
+    neck = build_neck(neck_cfg)
+    assert neck.deblocks[0][0].in_channels == 2
+    assert neck.deblocks[1][0].in_channels == 3
+    assert neck.deblocks[0][0].out_channels == 4
+    assert neck.deblocks[1][0].out_channels == 6
+    assert neck.deblocks[0][0].stride == (1, 1)
+    assert neck.deblocks[1][0].stride == (2, 2)
+    assert neck is not None
+
+    neck_cfg = dict(
+        type='SECONDFPN',
+        in_channels=[2, 2],
+        upsample_strides=[1, 2, 4],
+        out_channels=[2, 2],
+    )
+    with pytest.raises(AssertionError):
+        build_neck(neck_cfg)
+
+    neck_cfg = dict(
+        type='SECONDFPN',
+        in_channels=[2, 2, 4],
+        upsample_strides=[1, 2, 4],
+        out_channels=[2, 2],
+    )
+    with pytest.raises(AssertionError):
+        build_neck(neck_cfg)