Instructions to use BadMD/Pilot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BadMD/Pilot with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="BadMD/Pilot") 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("BadMD/Pilot") model = AutoModelForImageClassification.from_pretrained("BadMD/Pilot", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download app.py from BadMD/Pilot: direct link, hf CLI and curl.
- Browser
- Download file 844 Bytes
-
https://huggingface.co/BadMD/Pilot/resolve/refs%2Fpr%2F1/app.py
- Command line
-
hf download hf://BadMD/Pilot@refs/pr/1/app.py
-
curl -L -o app.py https://huggingface.co/BadMD/Pilot/resolve/refs%2Fpr%2F1/app.py
844 Bytes
| import torch | |
| from transformers import AutoModelForImageClassification, AutoFeatureExtractor | |
| import gradio as gr | |
| model_id = f'BadMD/Pilot' | |
| labels = ['daisy', 'dandelion', 'roses', 'sunflowers', 'tulips'] | |
| def classify_image(image): | |
| model = AutoModelForImageClassification.from_pretrained(model_id) | |
| feature_extractor = AutoFeatureExtractor.from_pretrained(model_id) | |
| inp = feature_extractor(image, return_tensors='pt') | |
| outp = model(**inp) | |
| pred = torch.nn.functional.softmax(outp.logits, dim=-1) | |
| preds = pred[0].cpu().detach().numpy() | |
| confidence = {label: float(preds[i]) for i, label in enumerate(labels)} | |
| return confidence | |
| interface = gr.Interface(fn=classify_image, | |
| inputs='image', | |
| examples=['flower-1.jpeg', 'flower-2.jpeg'], | |
| outputs='label').launch() |