Instructions to use dacanizalesconvers/material-surface-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dacanizalesconvers/material-surface-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="dacanizalesconvers/material-surface-classifier") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("dacanizalesconvers/material-surface-classifier") model = AutoModelForImageClassification.from_pretrained("dacanizalesconvers/material-surface-classifier") - timm
How to use dacanizalesconvers/material-surface-classifier with timm:
import timm model = timm.create_model("hf_hub:dacanizalesconvers/material-surface-classifier", pretrained=True) - Notebooks
- Google Colab
- Kaggle
| precision recall f1-score support | |
| asphalt 0.7391 0.8500 0.7907 20 | |
| concrete 0.6974 0.8833 0.7794 60 | |
| metal 0.4516 0.7000 0.5490 20 | |
| other 0.9676 0.8536 0.9070 280 | |
| wood 0.6087 0.7000 0.6512 20 | |
| accuracy 0.8425 400 | |
| macro avg 0.6929 0.7974 0.7355 400 | |
| weighted avg 0.8719 0.8425 0.8514 400 | |