Image Segmentation
Transformers
PyTorch
English
garment-mask-generation
image-inpainting
fashion
garment-mask
densepose
human-parsing
Instructions to use Ekliipce/wearit-garment-mask with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ekliipce/wearit-garment-mask with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="Ekliipce/wearit-garment-mask")# Load model directly from transformers import GarmentMaskPipeline model = GarmentMaskPipeline.from_pretrained("Ekliipce/wearit-garment-mask", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| # Copyright (c) Facebook, Inc. and its affiliates. | |
| # pyre-unsafe | |
| from detectron2.data import MetadataCatalog | |
| from detectron2.utils.file_io import PathManager | |
| from densepose import DensePoseTransformData | |
| def load_for_dataset(dataset_name): | |
| path = MetadataCatalog.get(dataset_name).densepose_transform_src | |
| densepose_transform_data_fpath = PathManager.get_local_path(path) | |
| return DensePoseTransformData.load(densepose_transform_data_fpath) | |
| def load_from_cfg(cfg): | |
| return load_for_dataset(cfg.DATASETS.TEST[0]) | |