How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
Paper • 2106.10270 • Published • 3
This model is a TensorFlow port of ViT B-16 [1] trained with recipes from [2]. ImageNet-1k dataset was used for training purposes. You can refer to this notebook to know how the porting was done.
References
[1] An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929
[2] How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers: https://arxiv.org/abs/2106.10270
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://probing-vits/vit_b16_patch16_224_i1k")