Instructions to use tzhao3/DeiT-CIFAR10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tzhao3/DeiT-CIFAR10 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="tzhao3/DeiT-CIFAR10") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("tzhao3/DeiT-CIFAR10") model = AutoModelForImageClassification.from_pretrained("tzhao3/DeiT-CIFAR10") - Notebooks
- Google Colab
- Kaggle
How is this model trained?
#2
by j35t3r - opened
Is this model pre-trained on ImageNet and fine-tuned on CIFAR-10?
I don't understand that here is image size 224
https://huggingface.co/tzhao3/DeiT-CIFAR10/tree/main
... but CIFAR-10 has image size 32x32 What is the AutoPreprocessor actually doing?
Yes, conduct preprocessing for your input, convert 3232 to 224224.