pytorchvideo/models/resnet.py [30:111]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - conv_b_num_groups: int = 1, conv_b_dilation: Tuple[int] = (1, 1, 1), conv_b: Callable = nn.Conv3d, conv_c: Callable = nn.Conv3d, # Norm configs. norm: Callable = nn.BatchNorm3d, norm_eps: float = 1e-5, norm_momentum: float = 0.1, # Activation configs. activation: Callable = nn.ReLU, ) -> nn.Module: """ Bottleneck block: a sequence of spatiotemporal Convolution, Normalization, and Activations repeated in the following order: :: Conv3d (conv_a) ↓ Normalization (norm_a) ↓ Activation (act_a) ↓ Conv3d (conv_b) ↓ Normalization (norm_b) ↓ Activation (act_b) ↓ Conv3d (conv_c) ↓ Normalization (norm_c) Normalization examples include: BatchNorm3d and None (no normalization). Activation examples include: ReLU, Softmax, Sigmoid, and None (no activation). Args: dim_in (int): input channel size to the bottleneck block. dim_inner (int): intermediate channel size of the bottleneck. dim_out (int): output channel size of the bottleneck. conv_a_kernel_size (tuple): convolutional kernel size(s) for conv_a. conv_a_stride (tuple): convolutional stride size(s) for conv_a. conv_a_padding (tuple): convolutional padding(s) for conv_a. conv_a (callable): a callable that constructs the conv_a conv layer, examples include nn.Conv3d, OctaveConv, etc conv_b_kernel_size (tuple): convolutional kernel size(s) for conv_b. conv_b_stride (tuple): convolutional stride size(s) for conv_b. conv_b_padding (tuple): convolutional padding(s) for conv_b. conv_b_num_groups (int): number of groups for groupwise convolution for conv_b. conv_b_dilation (tuple): dilation for 3D convolution for conv_b. conv_b (callable): a callable that constructs the conv_b conv layer, examples include nn.Conv3d, OctaveConv, etc conv_c (callable): a callable that constructs the conv_c conv layer, examples include nn.Conv3d, OctaveConv, etc norm (callable): a callable that constructs normalization layer, examples include nn.BatchNorm3d, None (not performing normalization). norm_eps (float): normalization epsilon. norm_momentum (float): normalization momentum. activation (callable): a callable that constructs activation layer, examples include: nn.ReLU, nn.Softmax, nn.Sigmoid, and None (not performing activation). Returns: (nn.Module): resnet bottleneck block. """ conv_a = conv_a( in_channels=dim_in, out_channels=dim_inner, kernel_size=conv_a_kernel_size, stride=conv_a_stride, padding=conv_a_padding, bias=False, ) norm_a = ( None if norm is None else norm(num_features=dim_inner, eps=norm_eps, momentum=norm_momentum) ) act_a = None if activation is None else activation() - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - pytorchvideo/models/resnet.py [165:250]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - conv_b_num_groups: int = 1, conv_b_dilation: Tuple[int] = (1, 1, 1), conv_b: Callable = nn.Conv3d, conv_c: Callable = nn.Conv3d, # Norm configs. norm: Callable = nn.BatchNorm3d, norm_eps: float = 1e-5, norm_momentum: float = 0.1, # Activation configs. activation: Callable = nn.ReLU, ) -> nn.Module: """ Acoustic Bottleneck block: a sequence of spatiotemporal Convolution, Normalization, and Activations repeated in the following order: :: Conv3d (conv_a) ↓ Normalization (norm_a) ↓ Activation (act_a) ↓ --------------------------------- ↓ ↓ Temporal Conv3d (conv_b) Spatial Conv3d (conv_b) ↓ ↓ Normalization (norm_b) Normalization (norm_b) ↓ ↓ Activation (act_b) Activation (act_b) ↓ ↓ --------------------------------- ↓ Conv3d (conv_c) ↓ Normalization (norm_c) Normalization examples include: BatchNorm3d and None (no normalization). Activation examples include: ReLU, Softmax, Sigmoid, and None (no activation). Args: dim_in (int): input channel size to the bottleneck block. dim_inner (int): intermediate channel size of the bottleneck. dim_out (int): output channel size of the bottleneck. conv_a_kernel_size (tuple): convolutional kernel size(s) for conv_a. conv_a_stride (tuple): convolutional stride size(s) for conv_a. conv_a_padding (tuple): convolutional padding(s) for conv_a. conv_a (callable): a callable that constructs the conv_a conv layer, examples include nn.Conv3d, OctaveConv, etc conv_b_kernel_size (tuple): convolutional kernel size(s) for conv_b. conv_b_stride (tuple): convolutional stride size(s) for conv_b. conv_b_padding (tuple): convolutional padding(s) for conv_b. conv_b_num_groups (int): number of groups for groupwise convolution for conv_b. conv_b_dilation (tuple): dilation for 3D convolution for conv_b. conv_b (callable): a callable that constructs the conv_b conv layer, examples include nn.Conv3d, OctaveConv, etc conv_c (callable): a callable that constructs the conv_c conv layer, examples include nn.Conv3d, OctaveConv, etc norm (callable): a callable that constructs normalization layer, examples include nn.BatchNorm3d, None (not performing normalization). norm_eps (float): normalization epsilon. norm_momentum (float): normalization momentum. activation (callable): a callable that constructs activation layer, examples include: nn.ReLU, nn.Softmax, nn.Sigmoid, and None (not performing activation). Returns: (nn.Module): resnet acoustic bottleneck block. """ conv_a = conv_a( in_channels=dim_in, out_channels=dim_inner, kernel_size=conv_a_kernel_size, stride=conv_a_stride, padding=conv_a_padding, bias=False, ) norm_a = ( None if norm is None else norm(num_features=dim_inner, eps=norm_eps, momentum=norm_momentum) ) act_a = None if activation is None else activation() - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -