Instructions to use facebook/deit-tiny-patch16-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/deit-tiny-patch16-224 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="facebook/deit-tiny-patch16-224") 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("facebook/deit-tiny-patch16-224") model = AutoModelForImageClassification.from_pretrained("facebook/deit-tiny-patch16-224") - Inference
- Notebooks
- Google Colab
- Kaggle
Accuracy Drop
#2
by mhyatt000 - opened
I tried to reproduce the results mentioned on this model card. Seems like my results do not match the claimed accuracy in the model card. I cannot figure out how to get the correct numbers, can you help me find my mistake?
- Claimed accuracy
- top 1: 72.2
- top 5: 91.1
- Received accuracy
- top 1: 66.5
- top 5: 87.7
Here are the details for my validation:
- I instantiate pre-trained model with
transformers.pipeline()and use measure top 1 / top 5 accuracy - Evaluation was performed on CPU.
- Dataset was downloaded from image-net.org