Model Training Tutorial

Welcome to the Model Training Tutorial! This tutorial will guide you through the process of training a model for snow cover detection. Take training Model One as an example. Follow the steps below to get started:

Step One: Set Up the Working Directory

Create a working directory named "train1" on your computer. Use the following command in the command line to create the directory:

mkdir data/train1

Navigate to the "data" directory to proceed with the next steps.

Step Two: Create Validation Dataset

Inside the "train1" directory, create a folder named "data" for your training dataset and another folder named "validation" for your validation dataset. Use the following commands in the command line:

mkdir train1/data
mkdir train1/validation

Step Three: Organize Validation Images

Inside the "train1/data/validation"& "train1/data/data" directory, create two folders named "snow" and "no" to store images with and without snow, respectively:

mkdir train1/data/data/no
mkdir train1/data/data/snow
mkdir train1/data/validation/no
mkdir train1/data/validation/snow

Organize your images into these folders accordingly.

Step Four: Install Required Libraries

Before training the model, make sure to install the necessary libraries and dependencies. Use the provided "requirements.txt" file to install the required packages. Navigate to the project directory and run the following command:

pip install -r requirements.txt

This command will install all the required libraries specified in the "requirements.txt" file.

Step Five: Run Model Training

Using your Python environment, run the Python program named "train.py" to start training the model. Use the following command:

python train.py

The training script will begin training the model based on the images in the "train1/data" directory, and validation will be performed using images in the "train1/validation" directory.