骨骼点动作识别-基于Paddle复现PoseC3D

class ResNet3d(nn.Layer):
    arch_settings = {
        50: (Bottleneck3d, (3, 4, 6, 3)),
        101: (Bottleneck3d, (3, 4, 23, 3)),
        152: (Bottleneck3d, (3, 8, 36, 3))
    }

    def __init__(self,
                 depth,
                 pretrained,
                 stage_blocks=None,
                 pretrained2d=True,
                 in_channels=3,
                 num_stages=4,
                 base_channels=64,
                 out_indices=(3, ),
                 spatial_strides=(1, 2, 2, 2),
                 temporal_strides=(1, 1, 1, 1),
                 dilations=(1, 1, 1, 1),
                 conv1_kernel=(3, 7, 7),
                 conv1_stride_s=2,
                 conv1_stride_t=1,
                 pool1_stride_s=2,
                 pool1_stride_t=1,
                 with_pool1=True,
                 with_pool2=True,
                 style='pytorch',
                 frozen_stages=-1,
                 inflate=(1, 1, 1, 1),
                 inflate_style='3x1x1',
                 conv_cfg=dict(type='Conv3d'),
                 norm_cfg=dict(type='BN3d', requires_grad=True),
                 act_cfg=dict(type='ReLU', inplace=True),
                 norm_eval=False,
                 with_cp=False,
                 non_local=(0, 0, 0, 0),
                 non_local_cfg=dict(),
                 zero_init_residual=True,
                 **kwargs):
        super().__init__()        if depth not in self.arch_settings:            raise KeyError(f'invalid depth {depth} for resnet')        # 初始化网络参数
        self.depth = depth
        self.pretrained = pretrained
        self.pretrained2d = pretrained2d
        self.in_channels = in_channels
        self.base_channels = base_channels
        self.num_stages = num_stages        assert 1 <= num_stages <= 4
        self.stage_blocks = stage_blocks
        self.out_indices = out_indices        assert max(out_indices) < num_stages
        self.spatial_strides = spatial_strides
        self.temporal_strides = temporal_strides
        self.dilations = dilations        assert len(spatial_strides) == len(temporal_strides) == len(
            dilations) == num_stages        if self.stage_blocks is not None:            assert len(self.stage_blocks) == num_stages        # 保存卷积网络参数
        self.conv1_kernel = conv1_kernel
        self.conv1_stride_s = conv1_stride_s
        self.conv1_stride_t = conv1_stride_t
        self.pool1_stride_s = pool1_stride_s
        self.pool1_stride_t = pool1_stride_t
        self.with_pool1 = with_pool1
        self.with_pool2 = with_pool2
        self.style = style
        self.frozen_stages = frozen_stages
        self.stage_inflations = _ntuple(num_stages)(inflate)
        self.non_local_stages = _ntuple(num_stages)(non_local)
        self.inflate_style = inflate_style
        self.conv_cfg = conv_cfg
        self.norm_cfg = norm_cfg
        self.act_cfg = act_cfg
        self.norm_eval = norm_eval
        self.with_cp = with_cp
        self.zero_init_residual = zero_init_residual

        self.block, stage_blocks = self.arch_settings[depth]        if self.stage_blocks is None:
            self.stage_blocks = stage_blocks[:num_stages]

        self.inplanes = self.base_channels

        self.non_local_cfg = non_local_cfg

        # 构建第一个 stem层
        self._make_stem_layer()

        self.res_layers = []        # 根据stage_blocks的内容构建网络。
        # 这里的stage_blocks是(3, 4, 6)。
        for i, num_blocks in enumerate(self.stage_blocks):
            spatial_stride = spatial_strides[i]
            temporal_stride = temporal_strides[i]
            dilation = dilations[i]
            planes = self.base_channels * 2**i
            res_layer = self.make_res_layer(
                self.block,
                self.inplanes,
                planes,
                num_blocks,
                spatial_stride=spatial_stride,
                temporal_stride=temporal_stride,
                dilation=dilation,
                style=self.style,
                norm_cfg=self.norm_cfg,
                conv_cfg=self.conv_cfg,
                act_cfg=self.act_cfg,
                non_local=self.non_local_stages[i],
                non_local_cfg=self.non_local_cfg,
                inflate=self.stage_inflations[i],
                inflate_style=self.inflate_style,
                with_cp=with_cp,
                **kwargs)
            self.inplanes = planes * self.block.expansion
            layer_name = f'layer{i + 1}'
            self.add_sublayer(layer_name, res_layer)
            self.res_layers.append(layer_name)

        self.feat_dim = self.block.expansion * self.base_channels * 2**(            len(self.stage_blocks) - 1)

def make_res_layer(block,
                       inplanes,
                       planes,
                       blocks,                       spatial_stride=1,                       temporal_stride=1,                       dilation=1,                       style='pytorch',                       inflate=1,                       inflate_style='3x1x1',                       non_local=0,                       non_local_cfg=dict(),                       norm_cfg=None,                       act_cfg=None,                       conv_cfg=None,                       with_cp=False,
                       **kwargs):
        inflate = inflate if not isinstance(inflate,
                                            int) else (inflate, ) * blocks
        non_local = non_local if not isinstance(
            non_local, int) else (non_local, ) * blocks
        assert len(inflate) == blocks and len(non_local) == blocks
        downsample = None
        # 判断是否需要进行下采样。当输入的通道和输出通道不相等，则根据planes * block.expansion缩减通道数。        if spatial_stride != 1 or inplanes != planes * block.expansion:
            downsample = ConvBNLayer(                in_channels=inplanes,                out_channels=planes * block.expansion,                kernel_size=1,
                stride=(temporal_stride, spatial_stride, spatial_stride),                bias=False,                act=None
            )

        layers = []
        layers.append(
            block(
                inplanes,
                planes,                spatial_stride=spatial_stride,                temporal_stride=temporal_stride,                dilation=dilation,                downsample=downsample,                style=style,
                inflate=(inflate[0] == 1),                inflate_style=inflate_style,
                non_local=(non_local[0] == 1),                non_local_cfg=non_local_cfg,                norm_cfg=norm_cfg,                conv_cfg=conv_cfg,                act_cfg=act_cfg,                with_cp=with_cp,
                **kwargs))
        inplanes = planes * block.expansion

        for i in range(1, blocks):
            layers.append(
                block(
                    inplanes,
                    planes,                    spatial_stride=1,                    temporal_stride=1,                    dilation=dilation,                    style=style,
                    inflate=(inflate[i] == 1),                    inflate_style=inflate_style,
                    non_local=(non_local[i] == 1),                    non_local_cfg=non_local_cfg,                    norm_cfg=norm_cfg,                    conv_cfg=conv_cfg,                    act_cfg=act_cfg,                    with_cp=with_cp,
                    **kwargs))

        return nn.Sequential(*layers)

class ConvBNLayer(nn.Layer):
    def __init__(
        self,
        in_channels,
        out_channels,
        kernel_size,        padding=0,        stride=1,        dilation=1,        groups=1,        act=None,        bias=None,
    ):
        super(ConvBNLayer, self).__init__()

        self._conv = nn.Conv3D(            in_channels=in_channels,            out_channels=out_channels,            kernel_size=kernel_size,            stride=stride,            padding=padding,            dilation=dilation,            groups=groups,            bias_attr=bias)

        self._batch_norm = nn.BatchNorm3D(out_channels, momentum=0.1)
        self.act = act        if act is not None:
            self._act_op = nn.ReLU()