Image Segmentation
Transformers
PyTorch
ONNX
Safetensors
Transformers.js
English
segformer
vision
nvidia/mit-b5
Instructions to use jayson1408/faceparsing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jayson1408/faceparsing with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="jayson1408/faceparsing")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, SegformerForSemanticSegmentation processor = AutoImageProcessor.from_pretrained("jayson1408/faceparsing") model = SegformerForSemanticSegmentation.from_pretrained("jayson1408/faceparsing", device_map="auto") - Transformers.js
How to use jayson1408/faceparsing with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-segmentation', 'jayson1408/faceparsing'); - Notebooks
- Google Colab
- Kaggle
Download onnx/model_quantized.onnx from jayson1408/faceparsing: direct link, hf CLI and curl.
- Browser
- Download file 89.4 MB
-
https://huggingface.co/jayson1408/faceparsing/resolve/main/onnx/model_quantized.onnx
- Command line
-
hf download hf://jayson1408/faceparsing/onnx/model_quantized.onnx
-
curl -L -o model_quantized.onnx https://huggingface.co/jayson1408/faceparsing/resolve/main/onnx/model_quantized.onnx
89.4 MB
- Xet hash:
- 4e9e78bea8fc68c0fc6a3a4af55059d8ffd20fcd267c6fcff130365226271e2d
- Size of remote file:
- 89.4 MB
- SHA256:
- 5bab9bfb3cb979f3098ac3b934b1641dbf87f835e0b03c2ca6d88dcf18c83d27
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.