Zero-Shot Object Detection
Transformers
PyTorch
TensorBoard
deformable_detr
object-detection
Generated from Trainer
zero-shot
Instructions to use mcity-data-engine/fisheye8k_facebook_deformable-detr-detic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mcity-data-engine/fisheye8k_facebook_deformable-detr-detic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-object-detection", model="mcity-data-engine/fisheye8k_facebook_deformable-detr-detic")# Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("mcity-data-engine/fisheye8k_facebook_deformable-detr-detic") model = AutoModelForObjectDetection.from_pretrained("mcity-data-engine/fisheye8k_facebook_deformable-detr-detic", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Improve model card with pipeline tag, links, sample usage, and expanded details
#3
by nielsr HF Staff - opened
This PR significantly enhances the model card by:
- Adding the
pipeline_tag: zero-shot-object-detectionand additionalobject-detection,zero-shottags to improve discoverability on the Hugging Face Hub. - Including direct links to the associated paper (Hugging Face Papers), the project page (
https://mcity.github.io/mcity_data_engine/), and the GitHub repository (https://github.com/mcity/mcity_data_engine). - Providing a practical Python code snippet for inference, demonstrating how to use the model for zero-shot object detection.
- Expanding the "Model description", "Intended uses & limitations", and "Training and evaluation data" sections with details from the paper's abstract and the GitHub README for better understanding of the model's purpose and application within the Mcity Data Engine.
- Incorporating "Acknowledgements" and "Citation" information from the GitHub repository.
- Removing the auto-generated comment.
danielbogdoll changed pull request status to merged