Image Segmentation
Transformers
Safetensors
English
mask2former
Electron-Microscopy
Ultrastructure-Segmentation
Semantic-Segmentation
Instructions to use Dnq2025/MicroStructFormer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Dnq2025/MicroStructFormer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="Dnq2025/MicroStructFormer")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation processor = AutoImageProcessor.from_pretrained("Dnq2025/MicroStructFormer") model = Mask2FormerForUniversalSegmentation.from_pretrained("Dnq2025/MicroStructFormer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download sample/sample_prediction.png from Dnq2025/MicroStructFormer: direct link, hf CLI and curl.
- Browser
- Download file 14.8 MB
-
https://huggingface.co/Dnq2025/MicroStructFormer/resolve/main/sample/sample_prediction.png
- Command line
-
hf download hf://Dnq2025/MicroStructFormer/sample/sample_prediction.png
-
curl -L -o sample_prediction.png https://huggingface.co/Dnq2025/MicroStructFormer/resolve/main/sample/sample_prediction.png
14.8 MB
- Xet hash:
- 88ed4a1e0f7bdd016af210163c1a71c9b516744ddcc85fdaae260abd0b705d10
- Size of remote file:
- 14.8 MB
- SHA256:
- c72b11ae84ff0a4af1fa7e21cc4ffbd1c970a6ada59e06fce784d8e4a2c8defd
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.