Args: cfg (CfgNode): instance_mode (ColorMode): parallel (bool): whether to run the model in different pr

The `__init__` method of any subclass should also contain these arguments. Args: in_channels (int): out_chann

The standard block type for ResNet18 and ResNet34. Args: in_channels (int): Number of input channels. out_cha

Args: norm (str or callable): a callable that takes the number of channels and return a `nn.Module`, or a pre-def

Similar to :class:`BottleneckBlock`, but with deformable conv in the 3x3 convolution.

Args: norm (str or callable): a callable that takes the number of channels and return a `nn.Module`, or a pre-def

Constructor for OIDEval. Args: lvis_gt (LVIS class instance, or str containing path of annotation file) lvis_dt (LVISR

Evaluate predictions. Fill self._results with the metrics of the tasks.

Initialize the weights

Compute the DICE loss, similar to generalized IOU for masks Args: inputs: A float tensor of arbitrary shape. The pred

Args: inputs: A float tensor of arbitrary shape. The predictions for each example. targets: A float tensor with t

Modified from detectron2.data.build.build_custom_train_loader, but supports different samplers

Modified from detectron2.data.build.build_custom_train_loader, but supports different samplers

Args: cfg: a detectron2 CfgNode Returns: backbone (Backbone): backbone module, must be a subclass of :class:`Backbone`.

Args: cfg: a detectron2 CfgNode Returns: backbone (Backbone): backbone module, must be a subclass of :class:`Backbone`.

Args: cfg: a detectron2 CfgNode Returns: backbone (Backbone): backbone module, must be a subclass of :class:`Backbone`.

Args: cfg: a detectron2 CfgNode Returns: backbone (Backbone): backbone module, must be a subclass of :class:`Backbone`.

Compute the DICE loss, similar to generalized IOU for masks Args: inputs: A float tensor of arbitrary shape. The pred