From fa2bfe4ef51912ccf4e30ba45183c575516fcf4f Mon Sep 17 00:00:00 2001
From: Lenoctambule <106790775+lenoctambule@users.noreply.github.com>
Date: Fri, 27 Mar 2026 09:05:01 +0100
Subject: [PATCH] feat: README.md w/ usage, training and inference instructions

---
 README.md | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)
 create mode 100644 README.md

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..edbd77e
--- /dev/null
+++ b/README.md
@@ -0,0 +1,39 @@
+# Python AutoEncoder from scratch using Numpy
+
+## Usage 
+
+1. Install requirements :
+```sh
+$ pip install -r requirements.txt
+```
+
+2. Optionally run mnist_test.py.
+```sh
+$ py mnist_test.py 
+```
+
+## Training
+
+Instatiate an `Autoencoder` object :
+```py
+from autoencoder import Autoencoder
+
+autoencoder = Autoencoder(in_len=300, bottleneck=50, 0.001, relu)
+```
+And then via the `train_dataset` method to train over a dataset :
+```py
+autoencoder.train_dataset(data)
+```
+Or via the `train` to input each data points iteratively :
+```py
+autoencoder.train(v)
+```
+
+## Inference
+
+Use your `Autoencoder` object with the `encode` and `decode` methods like so :
+```py
+example = ...
+code = autoencoder.encode(example)
+output = autoencoder.decode(code)
+```