/Detecting_Steel_Defects_with_Neural_Networks

This project explores using deep learning techniques to classify defects in images of steel in a real world business context. The entire project was done on AWS (S3 and Sagemaker). Designed and tuned artificial and convolutional neural networks. Achieved 85% accuracy in binary classification, and 79% accuracy in multiclass classification.

Primary LanguageJupyter Notebook

Stargazers