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

created by Zylo117

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

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

This class stores the segmentations for all objects in the image

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

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

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

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

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

Integration of multiple depth images using a TSDF.

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

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,

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 polygon

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

BatchNorm2d where the batch statistics and the affine parameters are fixed

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

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

Intrinsic parameters of a pinhole camera model. Attributes: width (int): The width in pixels of the camera. height(int): The heig

Intrinsic parameters of a pinhole camera model. Attributes: width (int): The width in pixels of the camera. height(int): The heig

Class to execute grasps on the Franka Emika fr3 robot.

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

Rigid spatial transform between coordinate systems in 3D space. Attributes: rotation (scipy.spatial.transform.Rotation) translati

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

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

modified by Zylo117

modified by Zylo117

This class is used to buffer gazebo RGBD camera set data and provide easy IO interface.

Grasp parameterized as pose of a 2-finger robot hand.

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

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.

Manage the scene object names, 3D representations, detections result, etc.

Rigid spatial transform between coordinate systems in 3D space. Attributes: rotation (scipy.spatial.transform.Rotation) translati

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

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

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.

From a list of samples from the dataset, returns the batched images and targets. This should be passed to the DataLoader