airiuz/SVHN_cropped

SVHN_dataset

The Street View House Numbers (SVHN) Dataset is an image digit recognition dataset of over 600,000 digit images coming from real world data. Images are cropped to 32x32.

Clone recursively

git clone https://github.com/airiuz/SVHN_dataset.git

Enter this file

cd SHVN_dataset

Install Virtual environment

To use the SHVN_dataset dataset, it is recommended to create a virtual environment in Python. You can do this by using the virtualenv package. First, install virtualenv using pip:

python -m pip install --user virtualenv

give a name this environment

python -m venv your_env

Activate this environment

your_env\Scripts\activate.bat

Install requirements

pip install -r requirement.txt

Open jupyter notebook

jupyter notebook

Run streamlit

streamlit run streamlit.py

Predict