Objective
Solve image classification with convolutional neural networks.
Task–101 imageClassification
Task-101 imageClassification
● This dataset consists of pictures of objects belonging to 101 classes.
● Each image is labelled with a single object.
● Each class contains roughly 40 to 800 images, totalling around 9k images.
● Images are of variable sizes, with typical edge lengths of 200-300 pixels.
● Training set: 5205 labeled images
● Validation set: 1736 labeled images
● Testing set: 1736 images(70% public)