Merge pull request #22 from gjbex/feature/pytorch

Add PyTorch MNIST example

Author: gjbex

source-code/README.md

@@ -19,6 +19,7 @@ to create it.  There is some material not covered in the presentation as well.
 
 ## What is it?
 * [`keras`](keras): illustration of using Keras for machine learning.
+* [`pytorch`](pytorch): illustration of using PyTorch for machine learning.
 * [`parameter-optimization`](parameter-optimization): example of parameter
   optimization kusing hyperopt, although the examples do not optimize
   hyperparameters in machine learning, that would be very similar.

source-code/pytorch/.gitignore

@@ -0,0 +1,4 @@
+# ignore data directory
+data/
+# ignore model checkpoints
+mnist_cnn.pt

source-code/pytorch/README.md

@@ -0,0 +1,21 @@
+# PyTorch
+
+PyTorch is a popular open-source machine learning library developed by
+Facebook's AI Research lab. It provides a flexible and dynamic computational
+graph, making it easy to build and train deep learning models. PyTorch is
+widely used in both academia and industry for various applications, including
+natural language processing, computer vision, and reinforcement learning.
+
+
+## What is it?
+
+1. `mnist.ipynb`: Jupyter notebook that demonstrates how to train a simple neural network on the
+   MNIST dataset using PyTorch. It includes code for loading the dataset,
+   defining the model architecture, training the model, and evaluating its
+   performance.
+1. `environment.yml`: Conda environment file that specifies the dependencies
+   required to run the `mnist.ipynb` notebook. It includes PyTorch and other
+   necessary libraries.
+1. `pytorch_linux64_conda_specs.txt`: Text file containing the specifications
+   for creating a Conda environment with PyTorch for Linux 64-bit systems.
+   It lists the required packages and their versions.

source-code/pytorch/environment.yml

@@ -0,0 +1,9 @@
+name: pytorch
+channels:
+  - conda-forge
+dependencies:
+  - jupyterlab
+  - pytorch
+  - torchvision
+
+prefix: "/home/gjb/mambaforge/envs/pytorch"