Image Segmentation
Transformers
PyTorch
ONNX
Safetensors
Transformers.js
English
segformer
vision
nvidia/mit-b5
Instructions to use jonathandinu/face-parsing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jonathandinu/face-parsing with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="jonathandinu/face-parsing")# Load model directly from transformers import AutoImageProcessor, SegformerForSemanticSegmentation processor = AutoImageProcessor.from_pretrained("jonathandinu/face-parsing") model = SegformerForSemanticSegmentation.from_pretrained("jonathandinu/face-parsing") - Transformers.js
How to use jonathandinu/face-parsing with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-segmentation', 'jonathandinu/face-parsing'); - Inference
- Notebooks
- Google Colab
- Kaggle
The demo of Transformers.js reports error
#5
by areyouokkk - opened
// each label is a separate mask object
// [
// { score: null, label: 'background', mask: transformers.js RawImage { ... }}
// { score: null, label: 'hair', mask: transformers.js RawImage { ... }}
// ...
// ]
for (const m of output) {
print(Found ${m.label});
m.mask.save(${m.label}.png);
}
the output is Uint8ClampedArray, why is different from your demo? And this Uint8ClampedArray is not a multiple of 4
Thanks!
