Create YOLOv3 using PyTorch from scratch (Part-1)
This is the start of a series on understanding and implementing the YOLOv3 model using PyTorch.
Category Python Programming
This category is not intended to be a comprehensive tutorial to Python, but a collection of tips, helpful code snippets and some Python projects that I think might be worth sharing.
Understanding transposed convolutions in PyTorch
This post explains transposed convolution and relevant module arguments in PyTorch.
How to Create Stunning Dot Pattern Portraits, using Python
In this post I share how to create a dot pattern portrait effect using Python, inspired by the same effect achieved using Photoshop.
Batch download and pre-process climate indices from the NOAA Physical Sciences Laboratory
This post introduces a simple Python script that batch downloads and processes climate indices from the NOAA PSL webpage.
A vectorized Mann-Kendall trend test implementation using numpy + scipy
In this post we are going to work out a vectorized Mann-Kendall trend test implementation using numpy and scipy.
Create a convolutional neural network using numpy
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.
Back-propagation in a convolution layer with numpy implementation
This post covers the derivations of back-propagation in a convolution layer, with numpy implementations.
2D and 3D pooling using numpy
This post covers the implementation of pooling layers in a convolutional neural network using numpy.
2D and 3D convolutions using numpy
This post will share some knowledge of 2D and 3D convolutions in a
convolution neural network (CNN), and 3 implementations all done using pure `numpy` and `scipy`.
Create a simple neural network using numpy
This post will share some basic knowledge of an artificial neural
network and how to create one from scratch using only numpy. We will build a classification network to
classify hand-written digits from the MNIST dataset.