A class that keeps all conversation history.

Very simple multi-layer perceptron (also called FFN)

An attention layer that allows for downscaling the size of the embedding after projection to queries, keys, and values.

Computes and stores the average and current value

This is a more standard version of the position embedding, very similar to the one used by the Attention is all you need paper, generalized t

Swin Transformer backbone. A PyTorch impl of : `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows` - https

A structure for storing masks and their related data in batched format. Implements basic filtering and concatenation.

Database class for nuImages to help query and retrieve information from the database.

A facility for config and config files. It supports common file formats as configs: python/json/yaml. The interface is the same as a dict obje

A facility for config and config files. It supports common file formats as configs: python/json/yaml. The interface is the same as a dict obje

Image to Patch Embedding.

Fake file-like stream object that redirects writes to a logger instance.

A list of video frames to be load asynchronously without blocking session start.

A basic Swin Transformer layer for one stage. Args: dim (int): Number of feature channels depth (int): Depths of this stage.

A basic Swin Transformer layer for one stage. Args: dim (int): Number of feature channels depth (int): Depths of this stage.

Collate examples for supervised fine-tuning.

接收一个类似train.md的文件 格式：**/ct_file.nii.gz, */seg_file.nii.gz

在原有PerceiverAttention基础上添加动态权重机制 保持原有接口，只增加动态调整功能

This class computes an assignment between the targets and the predictions of the network For efficiency reasons, the targets don't include the no_

Very simple multi-layer perceptron (also called FFN)

Multilayer perceptron.

Multilayer perceptron.

Image to Patch Embedding Args: patch_size (int): Patch token size. Default: 4. in_chans (int): Number of input image channel

Image to Patch Embedding Args: patch_size (int): Patch token size. Default: 4. in_chans (int): Number of input image channels. Def

Positional encoding using random spatial frequencies.

This class computes the loss for DETR. The process happens in two steps: 1) we compute hungarian assignment between ground truth boxes and

Swin Transformer Block. Args: dim (int): Number of input channels. num_heads (int): Number of attention heads. wind

Swin Transformer Block. Args: dim (int): Number of input channels. num_heads (int): Number of attention heads. window_size

Window based multi-head self attention (W-MSA) module with relative position bias. It supports both of shifted and non-shifted window. Ar

Window based multi-head self attention (W-MSA) module with relative position bias. It supports both of shifted and non-shifted window. Args:

自适应latent融合，在现有latent基础上增加动态性