Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Collection of assign results.

Applies padding to input (if needed) so that input can get fully covered by filter you specified. It support two modes "same" and "corner". The

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

CNN Feature Map Embedding Extract feature map from CNN, flatten, project to embedding dim.

CNN Feature Map Embedding Extract feature map from CNN, flatten, project to embedding dim.

CNN Feature Map Embedding Extract feature map from CNN, flatten, project to embedding dim.

A simple pipeline to load image.

Mask sampling result.

MLP as used in Vision Transformer, MLP-Mixer and related networks

Standard points generator for multi-level (Mlvl) feature maps in 2D points-based detectors. Args: strides (list[int] | list[tuple[int

Image to Patch Embedding.

Image to Patch Embedding.

Image to Patch Embedding

Image to Patch Embedding

Image to Patch Embedding.

The standard bottleneck residual block without the last activation layer. It contains 3 conv layers with kernels 1x1, 3x3, 1x1.

Bbox sampling result. Example: >>> # xdoctest: +IGNORE_WANT >>> from mmdet.core.bbox.samplers.sampling_result import * # NOQA

Vision Transformer with support for patch or hybrid CNN input stage.

Vision Transformer with support for patch or hybrid CNN input stage

Vision Transformer with support for patch or hybrid CNN input stage

Base assigner that assigns boxes to ground truth boxes.

Base class of samplers.

r"""Channel Mapper to reduce/increase channels of backbone features. This is used to reduce/increase channels of backbone features. Args:

ClsSoftmaxCost.Borrow from mmdet.core.bbox.match_costs.match_cost.ClassificationCost. Args: weight (int | float, optional): loss_we

ClsSoftmaxCost.Borrow from mmdet.core.bbox.match_costs.match_cost.ClassificationCost. Args: weight (int | float, optional): loss_we

CrossEntropyLoss. Args: use_sigmoid (bool, optional): Whether the prediction uses sigmoid of softmax. Defaults to False.

CrossEntropyLossCost. Args: weight (int | float, optional): loss weight. Defaults to 1. use_sigmoid (bool, optional): Whether the

Customized Text Logger hook. This logger prints out both lr and layer_0_lr.

Customized Text Logger hook. This logger prints out both lr and layer_0_lr.

Default formatting bundle. It simplifies the pipeline of formatting common fields, including "img" and "gt_semantic_seg". These fields are fo

Implements the DeformableDETR transformer. Args: as_two_stage (bool): Generate query from encoder features. Default: False.

Implements the decoder in DETR transformer. Args: return_intermediate (bool): Whether to return intermediate outputs. coder_norm_

Implements the decoder in DETR transformer. Args: return_intermediate (bool): Whether to return intermediate outputs. post_norm_c

Implements decoder layer in DETR transformer. Args: attn_cfgs (list[`mmcv.ConfigDict`] | list[dict] | dict )): Configs for se

TransformerEncoder of DETR. Args: post_norm_cfg (dict): Config of last normalization layer. Default： `LN`. Only used when `se

Cost of mask assignments based on dice losses. Args: weight (int | float, optional): loss_weight. Defaults to 1. pred_act (bool,

Cost of mask assignments based on dice losses. Args: weight (int | float, optional): loss_weight. Defaults to 1. pred_act (bool,

Deprecated optimizer hook for distributed training.

Implements Dynamic Convolution. This module generate parameters for each sample and use bmm to implement 1*1 convolution. Code is modified

Encoder Decoder segmentors. EncoderDecoder typically consists of backbone, decode_head, auxiliary_head. Note that auxiliary_head is only used

Encoder Decoder segmentors. EncoderDecoder typically consists of backbone, decode_head, auxiliary_head. Note that auxiliary_head is only used

Implements feed-forward networks (FFNs) with identity connection. Args: embed_dims (int): The feature dimension. Same as `Mult

FocalLossCost. Args: weight (int | float, optional): loss_weight alpha (int | float, optional): focal_loss alpha gamm

FocalLossCost. Args: weight (int | float, optional): loss_weight alpha (int | float, optional): focal_loss alpha gamm

Implementation of `HTC <https://arxiv.org/abs/1901.07518>`_

A LayerNorm variant, popularized by Transformers, that performs point-wise mean and variance normalization over the channel dimension for inp

Position embedding with learnable embedding weights. Args: num_feats (int): The feature dimension for each position along x-a