A conv block that bundles conv/norm/activation layers. This block simplifies the usage of convolution layers, which are commonly used with a

A registry to map strings to classes. Registered object could be built from registry. Example: >>> MODELS = Registry('models')

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

Depthwise separable convolution module. See https://arxiv.org/pdf/1704.04861.pdf for details. This module can replace a ConvModule with the

Normlize image by given mean and std.

Compose multiple transforms sequentially. Args: transforms (Sequence[dict | callable]): Sequence of transform object or confi

Subclass torch's LayerNorm to handle fp16.

Data class for intermediate outputs of BLIP models. image_embeds (torch.FloatTensor): Image embeddings, shape (batch_size, num_patches, embe

Feature fusion block.

Subclass torch's LayerNorm to handle fp16.

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). Args: drop_prob (float): Drop rate for path

Feature fusion block.

A general file client to access files in different backends. The client loads a file or text in a specified backend from its path and returns

InvertedResidual block for MobileNetV2. Args: in_channels (int): The input channels of the InvertedResidual block. out_channels (

ModuleList in openmmlab. Args: modules (iterable, optional): an iterable of modules to add. init_cfg (dict, optional): Initializa

Image to Patch Embedding

Track a series of values and provide access to smoothed values over a window or the global series average.

Interpolation module.

Subclass torch's LayerNorm to handle fp16.

Subclass torch's LayerNorm to handle fp16.

Class that manages loss scaling in mixed precision training which supports both dynamic or static mode. The implementation refers to http

Pooling Pyramid Module used in PSPNet. Args: pool_scales (tuple[int]): Pooling scales used in Pooling Pyramid Module.

A progress bar which can print the progress.

ResLayer to build ResNet style backbone. Args: block (nn.Module): block used to build ResLayer. inplanes (int): inplanes of block

Resize sample to given size (width, height).

A learnable scale parameter. This layer scales the input by a learnable factor. It multiplies a learnable scale parameter of shape (1,) with

Sequential module in openmmlab. Args: init_cfg (dict, optional): Initialization config dict.

The model can behave as an encoder (with only self-attention) as well as a decoder, in which case a layer of cross-attention is added between

The model can behave as an encoder (with only self-attention) as well as a decoder, in which case a layer of cross-attention is added between

Data class of features from BlipFeatureExtractor. Args: image_embeds: (torch.FloatTensor) of shape (batch_size, num_patches+1, embed

Data class of features from AlbefFeatureExtractor. Args: image_embeds: `torch.FloatTensor` of shape `(batch_size, 1, embed_dim)`, `o

A wrapper of concatenated dataset. Same as :obj:`torch.utils.data.dataset.ConcatDataset`, but concat the group flag for image aspect ratio.

Context Guided Block for CGNet. This class consists of four components: local feature extractor, surrounding feature extractor, joint feature

A container for any type of objects. Typically tensors will be stacked in the collate function and sliced along some dimension in the scatter

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).

Downsampling module for CGNet.

r"""KNN (CUDA) based on heap data structure. Modified from `PAConv <https://github.com/CVMI-Lab/PAConv/tree/main/ scene_seg/lib/pointops/src/k

Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`LlamaDecoderLayer`] Args: config: LlamaConfig

Image to Patch Embedding

Prepare sample for usage as network input.

Residual convolution module.

Residual convolution module.

Make a ANN used SelfAttentionBlock. Args: low_in_channels (int): Input channels of lower level feature, which is the key feat

A flexible Timer class. :Example: >>> import time >>> import annotator.uniformer.mmcv as mmcv >>> with mmcv.Timer(): >>> # s

Args: clip (torch.tensor, dtype=torch.uint8): Size is (C, T, H, W) Return: clip (torch.tensor, dtype=torch.float): Size is (T