## Understanding transposed convolutions in PyTorch

This post explains transposed convolution and relevant module arguments in PyTorch.

Number-Smithy

A Blog of Programming, Algorithms and Software Tools

Number-Smithy

A Blog of Programming, Algorithms and Software Tools

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.

This post explains transposed convolution and relevant module arguments in PyTorch.

In this post I share how to create a dot pattern portrait effect using Python, inspired by the same effect achieved using Photoshop.

This post introduces a simple Python script that batch downloads and processes climate indices from the NOAA PSL webpage.

In this post we are going to work out a vectorized Mann-Kendall trend test implementation using numpy and scipy.

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.

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`.

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.

`Gplot` is a (thin) wrapper around `matplotlib`, `basemap` and `cartopy` for quick and easy creations of geographical plots.