Instructions to use Taki3d/CrackDetectionLowRes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Taki3d/CrackDetectionLowRes with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Taki3d/CrackDetectionLowRes") 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("Taki3d/CrackDetectionLowRes") model = AutoModelForImageClassification.from_pretrained("Taki3d/CrackDetectionLowRes", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from Taki3d/CrackDetectionLowRes: direct link, hf CLI and curl.
- Browser
- Download file 204 Bytes
-
https://huggingface.co/Taki3d/CrackDetectionLowRes/resolve/refs%2Fpr%2F4/eval_results.json
- Command line
-
hf download hf://Taki3d/CrackDetectionLowRes@refs/pr/4/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/Taki3d/CrackDetectionLowRes/resolve/refs%2Fpr%2F4/eval_results.json
204 Bytes
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9940476190476191, | |
| "eval_loss": 0.018311450257897377, | |
| "eval_runtime": 686.6152, | |
| "eval_samples_per_second": 1.957, | |
| "eval_steps_per_second": 0.245 | |
| } |