Instructions to use XYZ9843/GOOSE-M2F with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use XYZ9843/GOOSE-M2F with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="XYZ9843/GOOSE-M2F")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation processor = AutoImageProcessor.from_pretrained("XYZ9843/GOOSE-M2F") model = Mask2FormerForUniversalSegmentation.from_pretrained("XYZ9843/GOOSE-M2F", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from XYZ9843/GOOSE-M2F: direct link, hf CLI and curl.
- Browser
- Download file 561 Bytes
-
https://huggingface.co/XYZ9843/GOOSE-M2F/resolve/refs%2Fpr%2F2/preprocessor_config.json
- Command line
-
hf download hf://XYZ9843/GOOSE-M2F@refs/pr/2/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/XYZ9843/GOOSE-M2F/resolve/refs%2Fpr%2F2/preprocessor_config.json
561 Bytes
| { | |
| "do_normalize": true, | |
| "do_pad": true, | |
| "do_reduce_labels": false, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "ignore_index": 0, | |
| "image_mean": [ | |
| 0.48500001430511475, | |
| 0.4560000002384186, | |
| 0.4059999883174896 | |
| ], | |
| "image_processor_type": "Mask2FormerImageProcessor", | |
| "image_std": [ | |
| 0.2290000021457672, | |
| 0.2239999920129776, | |
| 0.22499999403953552 | |
| ], | |
| "num_labels": 64, | |
| "reduce_labels": false, | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 576, | |
| "width": 1152 | |
| }, | |
| "size_divisor": 32 | |
| } |