Skip to content

Latest commit

 

History

History
50 lines (35 loc) · 1.51 KB

README.md

File metadata and controls

50 lines (35 loc) · 1.51 KB
Raw

UNet architecture for salt segmentation

Objective • Technologies • Usage •

First image test

Second image test

Third image test

🎯 Objectives

The current work presents convolutional neural networks being used for semantic segmentation of salt bodies on seismic volumes. The salt body could be used to extract seismic horizons or geobodies.

🛠 Technologies

The tools used in the construction of the project were:

👷 Usage

  • Follow the step-by-step to download and execute the code.
  • Pay attention, python3 version is 3.10.6 and pip version is 22.0.2.
# Commands used to start the project.
# Cloning the project
  # Method 1. Using HTTPS
https://github.com/algocompretto/unet.git
  # Method 2. Using SSH
git clone [email protected]:algocompretto/unet.git

# Creating the environment and download the packages
cd unet/
python3 -m venv .venv

  # Windows - Activating the environment
.venv\Scripts\activate.bat

  # POSIX - Activating the environment
source .venv/bin/activate

pip3 install -r requirements.txt

And then you are all set! Ready to train and evaluate the model.