calculate the f-score value. Args: precision (float | torch.Tensor): The precision value. recall (float | torch.Tensor): The reca

Place holder to format result to dataset specific output.

Forward function.

Forward function.

Args: feats (list[Tensor]): Feature maps of each level. Each has shape of (batch_size, c, h, w). Returns

x_list contains a list of tensors to nest together and run

Placeholder for Forward function for training.

Generate proposals from encoded memory. Args: memory (Tensor) : The output of encoder, has shape (bs, num_key, em

Get class weight for loss function. Args: class_weight (list[float] | str | None): If class_weight is a str, take it as a fil

Get class names of current dataset. Args: classes (Sequence[str] | str | None): If classes is None, use default C

Get one ground truth segmentation map for evaluation.

Get ground truth segmentation maps for evaluation.

Get the position embedding of proposal.

Get the reference points used in decoder. Args: spatial_shapes (Tensor): The shape of all feature maps, has shape

Compute classification and mask targets for all images for a decoder layer. Args: cls_scores_list (list[Tensor]): Mask sc

Compute classification and mask targets for all images for a decoder layer. Args: cls_scores_list (list[Tensor]): Mask sc

Compute classification and mask targets for all images for a decoder layer. Args: cls_scores_list (list[Tensor]): Mask sc

Estimate uncertainty based on pred logits. We estimate uncertainty as L1 distance between 0.0 and the logits prediction in 'mask_pred' for th

Get the valid radios of feature maps of all level.

Hue distortion.

Initialize layers of the DeformableDetrTransformer.

Initialize weight of later layer.

enumerate available model architectures based on config files

Returns the names of available CLIP models

return all models having the specified pretrain tag

Load annotation from directory. Args: img_dir (str): Path to image directory img_suffix (str): Suffix of images.

Load a CLIP model Parameters ---------- name : str A model name listed by `clip.available_models()`, or the path to a model check

Loss function. Args: all_cls_scores (Tensor): Classification scores for all decoder layers with shape [num_decode

Loss function. Args: all_cls_scores (Tensor): Classification scores for all decoder layers with shape [num_decode

Loss function. Args: all_cls_scores (Tensor): Classification scores for all decoder layers with shape [num_decode

Compute segmentation loss.

Pack all blocks in a stage into a ``ResLayer``.

make plugins for ResNet 'stage_idx'th stage . Currently we support to insert 'context_block', 'empirical_attention_block', 'nonlocal_

Calculate naive dice loss, the coefficient in the denominator is the first power instead of the second power. Args: pred (torch.Tenso

nn.Module: the normalization layer named "norm0"

nn.Module: the normalization layer named "norm1"

nn.Module: normalization layer after the first convolution layer

nn.Module: normalization layer after the second convolution layer

Serialize picklable python object to tensor.

PAM feature classification.

Convert pre-eval results to metrics. Args: pre_eval_results (list[tuple[torch.Tensor]]): per image eval results for computing

Performs any necessary transformations before tokenization. This method should pop the arguments from kwargs and return the remainin

Get testing data after pipeline. Args: idx (int): Index of data. Returns: dict: Testing data after pipeline

Get training data and annotations after pipeline. Args: idx (int): Index of data. Returns: dict: Training da

Forward function of PSP module.

Randomly select an img_scale from given candidates. Args: img_scales (list[tuple]): Images scales for selection. Returns