Skip to content

Latest commit

 

History

History
5 lines (4 loc) · 284 Bytes

README.md

File metadata and controls

5 lines (4 loc) · 284 Bytes

Image Classification using LeNet style architecture

  • Dataset: CINIC-10
  • Used mini-batch size of 64, a learning rate of 0.001 and the ADAM optimizer
  • Data Augmentation: enlarge the image by 10%, do a center crop by considering 90% of the image in the center, and flip the image.