Image Classification
Transformers
PyTorch
TensorBoard
beit
Generated from Trainer
Eval Results (legacy)
Instructions to use ChasingMercer/beit-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ChasingMercer/beit-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ChasingMercer/beit-base") 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("ChasingMercer/beit-base") model = AutoModelForImageClassification.from_pretrained("ChasingMercer/beit-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download all_results.json from ChasingMercer/beit-base: direct link, hf CLI and curl.
- Browser
- Download file 210 Bytes
-
https://huggingface.co/ChasingMercer/beit-base/resolve/main/all_results.json
- Command line
-
hf download hf://ChasingMercer/beit-base/all_results.json
-
curl -L -o all_results.json https://huggingface.co/ChasingMercer/beit-base/resolve/main/all_results.json
210 Bytes
| { | |
| "epoch": 3.0, | |
| "total_flos": 4.3513294045912105e+18, | |
| "train_loss": 0.08035437971183718, | |
| "train_runtime": 5091.7575, | |
| "train_samples_per_second": 11.034, | |
| "train_steps_per_second": 0.345 | |
| } |