Image Classification
Transformers
PyTorch
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Instructions to use johnnydevriese/vit-airplanes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use johnnydevriese/vit-airplanes with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="johnnydevriese/vit-airplanes") 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("johnnydevriese/vit-airplanes") model = AutoModelForImageClassification.from_pretrained("johnnydevriese/vit-airplanes", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download train_results.json from johnnydevriese/vit-airplanes: direct link, hf CLI and curl.
- Browser
- Download file 207 Bytes
-
https://huggingface.co/johnnydevriese/vit-airplanes/resolve/main/train_results.json
- Command line
-
hf download hf://johnnydevriese/vit-airplanes/train_results.json
-
curl -L -o train_results.json https://huggingface.co/johnnydevriese/vit-airplanes/resolve/main/train_results.json
207 Bytes
| { | |
| "epoch": 4.0, | |
| "total_flos": 2.067504813142917e+17, | |
| "train_loss": 0.04814572525875909, | |
| "train_runtime": 540.2683, | |
| "train_samples_per_second": 4.938, | |
| "train_steps_per_second": 0.311 | |
| } |