This post shows an *approximation method to compute the IoU between oriented 2D boxes*.
This post goes through the derivation of *signed distance function (SDF)* with respect to oriented boxes in 2D. I also showed *Python implementations* with some examples.
I implemented in Python an algorithm that fits the distribution of the sum of independent Gamma random variables.
This post talks about the binomial distribution with dependent trials, and Python implementation of the algorithm.
This post writes the training code of YOLOv3 and carries out some test training sessions on COCO 2014 dataset.
In this post we create a Dataset and a DataLoader class to load the COCO 2014 detection data.
In this post we create 3 essential tools in the object detection task: IoU (Intersection-over-Union), NMS (Non-Maximum suppression) and mAP (mean Average Precision).
In this post we load pre-trained weights for the YOLOv3 model and run some test inferences.
This post talks about reading and parsing the YOLOv3 config file and building a Darknet-53 model using PyTorch.
This is the start of a series on understanding and implementing the YOLOv3 model using PyTorch.