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

A predictor that runs the model asynchronously, possibly on >1 GPUs. Because rendering the visualization takes considerably amount of time,

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

A callable which takes a dataset dict in Detectron2 Dataset format, and map it into a format used by DiffusionInst. The callable current

A DiffusionInst with test-time augmentation enabled. Its :meth:`__call__` method has the same interface as :meth:`DiffusionInst.forwa

Model Exponential Moving Average Keep a moving average of everything in the model state_dict (parameters and buffers). This is intended to all

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

Multilayer perceptron.

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

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

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

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

Extension of the Trainer class adapted to DiffusionInst.

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

A fully connected layer that reshapes outputs to feature maps.

Implement DiffusionInst

Gaussian random features for encoding time steps.

This module is used in RetinaNet to generate extra layers, P6 and P7 from C5 feature.

Patch Merging Layer Args: dim (int): Number of input channels. norm_layer (nn.Module, optional): Normalization layer. Default: n