Image网 (pronounced Imagewang; 网 means "net" in Chinese) is an image classification dataset combined from Imagenette and Imagewoof datasets in a way to make it into a semi-supervised unbalanced classification problem:
the validation set is the same as the validation set of Imagewoof; there are no Imagenette images in the validation set (they're all in the training set),
only 10% of Imagewoof images are in the training set. The remaining images are in the "unsupervised" split.
Paper | Code | Results | Date | Stars |
---|