| There are two approaches to depth estimation: | |
| stereo: depths are estimated by comparing two images of the same image from slightly different angles | |
| monocular: depths are estimated from a single image | |
| from transformers import pipeline | |
| depth_estimator = pipeline(task="depth-estimation") | |
| preds = depth_estimator( | |
| "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg" | |
| ) | |
| Natural language processing | |
| NLP tasks are among the most common types of tasks because text is such a natural way for us to communicate. |