This class represents a set of bounding boxes. The bounding boxes are represented as a Nx4 Tensor. In order to uniquely determine the

created by Zylo117

Pooler for Detection with or without FPN. It currently hard-code ROIAlign in the implementation, but that can be made more generic lat

This class stores the segmentations for all objects in the image

created by Zylo117 The real keras/tensorflow conv2d with same padding

A helper class for managing registering modules, it extends a dictionary and provides a register functions. Eg. creeting a registry:

This class encodes and decodes a set of bounding boxes into the representation used for training the regressors.

This class assigns to each predicted "element" (e.g., a box) a ground-truth element. Each predicted element will have exactly zero or one m

created by Zylo117 The real keras/tensorflow MaxPool2d with same padding

Projects a set of masks in an image on the locations specified by the bounding boxes

This class holds a set of polygons that represents a single instance of an object mask. The object can be represented as a set of poly

Standard convolution block with Batch normalization and activation. Parameters: ---------- in_channels : int Number of

r"""Randomly zeroes 2D spatial blocks of the input tensor. As described in the paper `DropBlock: A regularization method for convolutional

This class samples batches, ensuring that they contain a fixed proportion of positives

This class takes as input a set of embeddings of dimension C1 and outputs a set of embedding of dimension C2, after a linear transformation

BatchNorm2d where the batch statistics and the affine parameters are fixed

Structure that holds a list of images (of possibly varying sizes) as a single tensor. This works by padding the images to the same siz

In PyTorch<=1.5, ``nn.SyncBatchNorm`` has incorrect gradient when the batch size on each worker is different. (e.g., when scale augmen

config files. only support .py file as config now. ref: mmcv.utils.config Example: >>> cfg = Config(dict(a=1, b=dict(b1=[0,

For a set of image sizes and feature maps, computes a set of anchors

Base class for model's outputs that also contains a pooling of the last hidden states. Args: last_hidden_state (`torch.FloatTensor`

modified by Zylo117

Return features in every fpn level.

modified by Zylo117

For each target category, extract one roi feature on each scale, i.e., (batch, scales, latents, dim_v), latents always = k shot. "latents" de

Mobile Inverted Residual Bottleneck Block Args: block_args (namedtuple): BlockArgs, see above global_params (namedtuple

Very simple multi-layer perceptron (also called FFN)

This class is unfinished and not meant for use yet It is supposed to contain the mask for an object as a 2d tensor

Multilayer perceptron.

Multilayer perceptron.

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

adapted and modified from https://github.com/google/automl/blob/master/efficientdet/anchors.py by Zylo117

Computes and stores the average and current value

From a list of samples from the dataset, returns the images and targets. Images should be converted to batched images in `im_detect_bb

ResNet backbone with frozen BatchNorm.

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.

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.

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