Hurricane Wind Speed Regressor

Hurricane Wind Speed Regressor

Predicts hurricane wind speed with a fine-tuned ResNet50 model in a Gradio app. It suits students, researchers and developers who want to see an image regression model at work.

Made by nakulmital 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: Hurricane Wind Speed Regressor is a Gradio app that predicts hurricane wind speed with a fine-tuned ResNet50 model. The Space names one model, nakulmital/ResNet50-Hurricane-WindSpeed-Regressor. The repository holds app.py, model.py, requirements.txt and a README.

Who it suits: People who want to see a small regression model estimate a weather number, and who can read a short Python app.

Industry | Who uses it | How they use it | Example
Education | Data science students | See a fine-tuned network predict a number | A class project demo
Research | Weather hobbyists | Try an image based estimate of wind speed | A hurricane picture
Software | Developers | Read how model.py and app.py serve a regressor | Opening the two files
Teaching | Instructors | Show the difference between regression and classification | A short lecture demo

If you need an official forecast, you can skip it, since this is a model demo.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• Python 3.12 on your own Windows, macOS or Linux computer, using a downloaded copy

Use case | Who | What they get back
Wind speed estimate | Students | A predicted wind speed number
Model study | Developers | A small fine-tuned ResNet50 app to read
Teaching demo | Instructors | A live regression example for a class

How to set it up:

• Python 3.12
• Python packages from requirements.txt, with Gradio 6.31.0
• At Hugging Face the Space runs on zero-a10g hardware, so a copy may want a similar GPU

1. Install the Hugging Face hub package.
2. Download the Space with the hf command.
3. Move into the downloaded folder.
4. Install Gradio 6.31.0, then the requirements.
5. Start app.py.

pip install -U huggingface_hub
hf download nakulmital/Hurricane_Wind_Speed_Regressor --repo-type space --local-dir Hurricane_Wind_Speed_Regressor
cd Hurricane_Wind_Speed_Regressor
pip install gradio==6.31.0
pip install -r requirements.txt
python app.py

How to use it: Online, open the Space page and use the screen there. On your own computer, start the app with the command below and use the screen it opens.

python app.py

Example: You give the app a hurricane image and run it. The source does not show the screen, but ResNet50 is an image network, so the app should return a predicted wind speed for that picture.

For newcomers and experts: Open the Space page and try one picture. A regressor outputs a number instead of a label, so the answer is a wind speed value.

The model is a ResNet50 fine-tuned for wind speed, and model.py sits next to app.py in the repository. The source gives no accuracy figures, units or training data details, so treat any prediction as a demo result.

You give the app an image
app.py passes it to the ResNet50 regressor
The model predicts a wind speed
The value is shown on the screen

Good to know:

• Hardware: zero-a10g at Hugging Face, with Gradio 6.31.0 and Python 3.12
• License: mit
• Cost to run: none named
• Data it reaches: the image you give it, plus the model it names
• Not for: official forecasts or safety decisions, as the source gives no accuracy figures

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/nakulmital/Hurricane_Wind_Speed_Regressor
• Files: https://huggingface.co/spaces/nakulmital/Hurricane_Wind_Speed_Regressor/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.