Vision Transformer (ViT) for Music Genre Classification

Model Overview

It achieves the following results on the evaluation set:

  • Loss: 0.8358
  • Accuracy: 0.7460
Downloads last month
66
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for ghermoso/vit-eGTZANplus

Finetuned
(1968)
this model

Dataset used to train ghermoso/vit-eGTZANplus