A Conv2d -> Batchnorm -> silu/leaky relu block

COCO dataset class.

Lightnet dataloader that enables on the fly resizing of the images. See :class:`torch.utils.data.DataLoader` for more information on the argu

This batch sampler will generate mini-batches of (dim, index) tuples from another sampler. It works just like the :class:`torch.utils.data.sa

In training, we only care about the "infinite stream" of training data. So this sampler produces an infinite stream of indices and all wo

Detection dataset wrapper that performs mixup for normal dataset.

COCO AP Evaluation class. All the data in the val2017 dataset are processed and evaluated by COCO API.

Defines the transformations that should be applied to test PIL image for input into the network dimension -> tensorize -> color adj

C3 in yolov5, CSP Bottleneck with 3 convolutions

A simple Kalman filter for tracking bounding boxes in image space. The 8-dimensional state space x, y, a, h, vx, vy, va, vh conta

A simple Kalman filter for tracking bounding boxes in image space. The 8-dimensional state space x, y, a, h, vx, vy, va, vh co

A simple Kalman filter for tracking bounding boxes in image space. The 8-dimensional state space x, y, a, h, vx, vy, va, vh co

COCO AP Evaluation class. All the data in the val2017 dataset are processed and evaluated by COCO API.

A simple timer.

YOLOv3 model. Darknet 53 is the default backbone of this model.

YOLOX model module. The module list is defined by create_yolov3_modules function. The network returns loss values from three YOLO layers duri

A simple Kalman filter for tracking bounding boxes in image space. The 8-dimensional state space x, y, a, h, vx, vy, va, vh co

A simple Kalman filter for tracking bounding boxes in image space. The 8-dimensional state space x, y, a, h, vx, vy, va, vh co

A simple Kalman filter for tracking bounding boxes in image space. The 8-dimensional state space x, y, a, h, vx, vy, va, vh conta

A simple Kalman filter for tracking bounding boxes in image space. The 8-dimensional state space x, y, a, h, vx, vy, va, vh co

Spatial pyramid pooling layer used in YOLOv3-SPP

DataPrefetcher is inspired by code of following file: https://github.com/NVIDIA/apex/blob/master/examples/imagenet/main_amp.py It could s

This class represents a bounding box detection in a single image. Parameters ---------- tlwh : array_like Bounding box in for

Focus width and height information into channel space.

This class represents the internal state of individual tracked objects observed as bbox.

A simple Kalman filter for tracking bounding boxes in image space. The 8-dimensional state space x, y, a, h, vx, vy, va, vh co

Computes and stores the average and current value

Model Exponential Moving Average from https://github.com/rwightman/pytorch-image-models Keep a moving average of everything in the model stat

Residual layer with `in_channels` inputs.

stream object that redirects writes to a logger instance.

A single target track with state space `(x, y, a, h)` and associated velocities, where `(x, y)` is the center of the bounding box, `a` is the

This module converts the model's output into the format expected by the coco api

This module converts the model's output into the format expected by the coco api

YOLOFPN module. Darknet 53 is the default backbone of this model.

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

Basic class for any experiment.