- 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.
nikhitmago / image-classification Goto Github PK
View Code? Open in Web Editor NEWCreate, train and test a CNN for the task of image classification