Instructions to use infinite000/roadwork_detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use infinite000/roadwork_detection with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="infinite000/roadwork_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("infinite000/roadwork_detection") model = AutoModelForImageClassification.from_pretrained("infinite000/roadwork_detection", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload model_card.json with huggingface_hub
Browse files- model_card.json +25 -4
model_card.json
CHANGED
|
@@ -1,5 +1,26 @@
|
|
| 1 |
-
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "vit-roadwork-improved",
|
| 3 |
+
"description": "Improved ViT model with validator augmentations",
|
| 4 |
+
"version": "2.0.0",
|
| 5 |
+
"training_date": "2026-02-12 08:56:42",
|
| 6 |
+
"base_model": "./checkpoints/upload_model_only",
|
| 7 |
+
"training_config": {
|
| 8 |
+
"learning_rate": 1e-05,
|
| 9 |
+
"num_epochs": 15,
|
| 10 |
+
"batch_size": 32,
|
| 11 |
+
"augmentation_prob": 0.95,
|
| 12 |
+
"use_validator_augmentations": false
|
| 13 |
+
},
|
| 14 |
+
"performance": {
|
| 15 |
+
"eval_loss": 0.09602824598550797,
|
| 16 |
+
"eval_accuracy": 0.9792,
|
| 17 |
+
"eval_precision": 0.9842829076620825,
|
| 18 |
+
"eval_recall": 0.9901185770750988,
|
| 19 |
+
"eval_f1": 0.987192118226601,
|
| 20 |
+
"eval_auc": 0.9871624539143722,
|
| 21 |
+
"eval_runtime": 42.2308,
|
| 22 |
+
"eval_samples_per_second": 14.8,
|
| 23 |
+
"eval_steps_per_second": 0.474,
|
| 24 |
+
"epoch": 10.884353741496598
|
| 25 |
+
}
|
| 26 |
}
|