Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Instructions to use arpanl/Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use arpanl/Model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="arpanl/Model") 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("arpanl/Model") model = AutoModelForImageClassification.from_pretrained("arpanl/Model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from arpanl/Model: direct link, hf CLI and curl.
- Browser
- Download file 240 Bytes
-
https://huggingface.co/arpanl/Model/resolve/main/eval_results.json
- Command line
-
hf download hf://arpanl/Model/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/arpanl/Model/resolve/main/eval_results.json
240 Bytes
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.14285714285714285, | |
| "eval_f1": 0.024242424242424246, | |
| "eval_loss": 3.5492660999298096, | |
| "eval_runtime": 85.1371, | |
| "eval_samples_per_second": 0.164, | |
| "eval_steps_per_second": 0.023 | |
| } |