apsora commited on
Commit
7ffe8ba
·
verified ·
1 Parent(s): 7084745

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +14 -16
README.md CHANGED
@@ -1,16 +1,14 @@
1
- # 🧱 LEGO Brick Classifier — Gradio Space
2
-
3
- This Space wraps a trained **AutoGluon** tabular model that classifies LEGO pieces as **Standard**, **Flat**, or **Sloped** from four inputs: **Length, Height, Width, Studs**.
4
-
5
- - **Model repo:** `Iris314/classical-automl-model` (uses `lego_predictor_dir.zip`)
6
- - **Dataset:** `aedupuga/lego-sizes`
7
- - **Model type:** AutoML ensemble (best = LightGBM)
8
- - **Purpose:** Coursework demo for classical ML + Gradio
9
-
10
- ## How it works
11
- - Downloads the predictor from the model repo via `huggingface_hub`.
12
- - Renames UI features to the training schema: `Length → Max Length (cm)`, `Height → Max Height (cm)`, `Width → Width (cm)`, keeps `Studs`.
13
- - Runs `predict_proba` and shows a top-3 probability label.
14
-
15
- ## Notes
16
- - This is a teaching demo; dataset is small/synthetic. Not for production.
 
1
+ ---
2
+ title: 🧱 LEGO Brick Classifier
3
+ emoji: 🧩
4
+ colorFrom: blue
5
+ colorTo: indigo
6
+ sdk: gradio
7
+ sdk_version: "4.44.0"
8
+ app_file: app.py
9
+ pinned: false
10
+ ---
11
+
12
+ # 🧱 LEGO Brick Classifier
13
+ Predict whether a LEGO brick is **Standard**, **Flat**, or **Sloped** using an AutoGluon model.
14
+ Built with ❤️ using Gradio and Hugging Face Spaces.