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.
This post explains transposed convolution and relevant module arguments in PyTorch.
In this post we put together all the building blocks covered in previous posts to create a convolution neural network, using numpy, and test it on the MNIST hand-written digits classification task.
This post covers the derivations of back-propagation in a convolution layer, with numpy implementations.
This post covers the implementation of pooling layers in a convolutional neural network using numpy.