Image Segmentation
Transformers
PyTorch
modnet
feature-extraction
image-matting
background-removal
computer-vision
custom-architecture
custom_code
Instructions to use boopathiraj/MODNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use boopathiraj/MODNet with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="boopathiraj/MODNet", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("boopathiraj/MODNet", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| import torch | |
| from torch import nn | |
| from transformers import PreTrainedModel, PretrainedConfig | |
| from .configuration_modnet import MODNetConfig | |
| from .modnet import MODNet | |
| class HF_MODNet(PreTrainedModel): | |
| config_class = MODNetConfig | |
| def __init__(self, config): | |
| super().__init__(config) | |
| self.modnet = MODNet(backbone_pretrained=False) | |
| def forward(self, x, inference=True): | |
| return self.modnet(x, inference) |