Image Classification
Transformers
PyTorch
TensorBoard
vit
vision
Generated from Trainer
Eval Results (legacy)
Instructions to use fumi13/vit-base-beans with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fumi13/vit-base-beans with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="fumi13/vit-base-beans") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("fumi13/vit-base-beans") model = AutoModelForImageClassification.from_pretrained("fumi13/vit-base-beans", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from fumi13/vit-base-beans: direct link, hf CLI and curl.
- Browser
- Download file 202 Bytes
-
https://huggingface.co/fumi13/vit-base-beans/resolve/main/eval_results.json
- Command line
-
hf download hf://fumi13/vit-base-beans/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/fumi13/vit-base-beans/resolve/main/eval_results.json
202 Bytes
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9924812030075187, | |
| "eval_loss": 0.08238118141889572, | |
| "eval_runtime": 2.4987, | |
| "eval_samples_per_second": 53.227, | |
| "eval_steps_per_second": 6.804 | |
| } |