Quickdraw

Quickdraw

Recognizes hand-drawn sketches with a saved model in a Gradio page, for people who want to try a small doodle classifier or study a simple image demo.

Made by hitchhiker3010 on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Quickdraw is a Gradio app that, by its name, recognizes hand-drawn sketches. It runs a saved model stored in model.pkl. The record does not say which drawings or categories the model knows.

Who it suits: It suits people who like to try doodle recognition and developers who want a tiny Gradio example with one model file. The record has no description beyond the file list, so look at the page for what it accepts.

Industry | Who uses it | How they use it | Example
Education | Students of machine learning | See an image classifier running in a web page | Draw a quick sketch and read the guess
Software | Python developers | Copy a minimal app with a saved model | Read app.py next to model.pkl
Hobby projects | Curious makers | Test how well a model reads rough drawings | Try the same object drawn two ways

You can skip it if you need a documented recognizer with known categories.

Where to use it:

• A web browser, on the Space's page on Hugging Face
• Python 3.7.12 on Windows, macOS or Linux, from a downloaded copy

Use case | Who | What they get back
Try sketch recognition | Anyone | The model's guess for a drawing
Study a minimal demo | Learners | A small app, one model file and a package list
Reuse as a base | Developers | A starting folder for their own classifier

How to set it up:

• Nothing at all if you use the online Space
• Python 3.7.12 on your computer, only if you run a copy
• The packages listed in requirements.txt

1. Open the Space's page in a browser to use it with nothing to install.
2. To run a copy, install the Hugging Face Hub package and download the Space.
3. Move into the new folder, then install Gradio and the listed requirements.
4. Start the app with Python.

pip install -U huggingface_hub
hf download hitchhiker3010/quickdraw --repo-type space --local-dir quickdraw
cd quickdraw
pip install gradio
pip install -r requirements.txt
python app.py

How to use it: Online, open the Space and use the controls on its page. On your own machine, run the main file from the Space folder, then use the page it serves. The record does not list the controls, so look at the page.

python app.py

Example: You open the Space and give it a quick sketch of an everyday object. The app returns the model's guess at what the drawing shows. The record shows no sample, so check the page for how to provide the drawing.

For newcomers and experts: A classifier looks at an input and picks the label it fits best. Start by opening the Space and drawing something simple to see what the model says.

If you know the field, the app loads a pickled model from model.pkl and serves it with Gradio. The record pins an older Python version, 3.7.12, so a modern setup may need a matching environment. No accuracy figures are given.

You draw or upload a sketch
The Gradio page sends it to app.py
The model in model.pkl scores it
The page shows the guess

Good to know:

• License: afl-3, as listed on the Space
• Cost to run: none named
• Data it reaches: the drawing you give it and the saved model file
• Not for: the record names no exclusions, and gives no list of categories or accuracy figures

On Hugging Face, 13 November 2026

• Likes: 0
• Built with: gradio
• License: afl-3.0

Links

• Space: https://huggingface.co/spaces/hitchhiker3010/quickdraw
• Files: https://huggingface.co/spaces/hitchhiker3010/quickdraw/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.