raoofnaushad / UNET_SALT_DETECTION

Competition Overview - Source: Kaggle Several areas of Earth with large accumulations of oil and gas also have huge deposits of salt below the surface. But unfortunately, knowing where large salt deposits are precisely is very difficult. Professional seismic imaging still requires expert human interpretation of salt bodies. This leads to very subjective, highly variable renderings. More alarmingly, it leads to potentially dangerous situations for oil and gas company drillers. To create the most accurate seismic images and 3D renderings, TGS (the world's leading geoscience data company) is hoping Kaggle's machine learning community will be able to build an algorithm that automatically and accurately identifies if a subsurface target is salt or not.

UNET for Salt Detection

You can download the dataset from Kaggle Deep Learning Competition - TGS Salt Identification Challenge

For more details about the implementation checkout the blog : UNET for Semantic Segmentation - Implementation from Scratch

For implementation:

• Install requirements.txt
• Run the notebook to generate the model.
• Dataset can be downloaded from the link. In this notebook we only use train.zip
• Save model in the root directory
• Do the inference in notebook

Let me know the comments and corrections please.