Liam’s Learning

100 Days Of PyTorch
Posts

About

Home

Exploring machine learning, data science, and math through self-study and blogging.

Keywords

Blog, Machine learning blog, Deep learning blog, Data science blog, Math blog, PyTorch blog, Machine learning, Deep learning, Data Science, Math

Welcome

Hi, I’m Liam, a Dutchie studying machine learning and mathematics.

This blog is a place where I explain what I’m learning, work through complex topics, and share insights that might help others learning too.

Whether you’re just starting out or deep into the field, I hope you find something useful here.

Recent posts

Day 6: PyTorch Basics - Deploying Model to HuggingFace Spaces With Gradio and ONNX

Deploying your model might seem like a daunting task, and in some cases, it certainly is. But it is arguably one of the most import things to learn, since a model that never…

Day 5: PyTorch Basics - Saving and Loading Models

Previously, we learned how to train a neural network model. But how do we actually make predictions with it? And how can we use open-source models that other people trained?…

Day 4 - PyTorch Basics: Building and Training a Neural Network

Learn how to use torch.nn to build the neural network structure, and how to train the model to recognize images, using a training and evaluation loop. It assumes you are…

Day 3: Pytorch Basics - Transforms

Data comes in many different formats. On the other hand, PyTorch can only do machine learning with one data type, the tensor. Transforms can convert any data to a tensor. In…

Day 2: PyTorch Basics - Dataset and DataLoader

In this post we learn about how to download datasets with PyTorch Datasets, and how to retrieve data from them for training an ML model while keeping data and model…

Day 1: Pytorch Basics - Tensors

Tensors lie at the heart of PyTorch. If we want to be proficient in PyTorch, we need to know what we can do with the Tensor object. There are over 1200 possible operations…

Backpropagation: How Does Your Computer Calculate Gradients?

How backpropagation is used to compute gradients in neural networks, using computational graphs and the chain rule.

No matching items