Instructions to use Bazaar/cv_solar_panel_defect_detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Bazaar/cv_solar_panel_defect_detection with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Bazaar/cv_solar_panel_defect_detection") 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("Bazaar/cv_solar_panel_defect_detection") model = AutoModelForImageClassification.from_pretrained("Bazaar/cv_solar_panel_defect_detection", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from Bazaar/cv_solar_panel_defect_detection: direct link, hf CLI and curl.
- Browser
- Download file 855 Bytes
-
https://huggingface.co/Bazaar/cv_solar_panel_defect_detection/resolve/main/config.json
- Command line
-
hf download hf://Bazaar/cv_solar_panel_defect_detection/config.json
-
curl -L -o config.json https://huggingface.co/Bazaar/cv_solar_panel_defect_detection/resolve/main/config.json
855 Bytes
| { | |
| "_name_or_path": "google/vit-base-patch16-224-in21k", | |
| "architectures": [ | |
| "ViTForImageClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "encoder_stride": 16, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "medium defect", | |
| "1": "minor defect", | |
| "2": "no defect", | |
| "3": "serious defect" | |
| }, | |
| "image_size": 224, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "medium defect": "0", | |
| "minor defect": "1", | |
| "no defect": "2", | |
| "serious defect": "3" | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "model_type": "vit", | |
| "num_attention_heads": 12, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "patch_size": 16, | |
| "problem_type": "single_label_classification", | |
| "qkv_bias": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.32.0" | |
| } | |