Image Segmentation
Transformers
PyTorch
ONNX
Safetensors
SegformerForSemanticSegmentation
remove background
background
background-removal
Pytorch
vision
legal liability
custom_code
Instructions to use OwlMaster/FixRM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OwlMaster/FixRM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="OwlMaster/FixRM", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForImageSegmentation model = AutoModelForImageSegmentation.from_pretrained("OwlMaster/FixRM", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download onnx/quantize_config.json from OwlMaster/FixRM: direct link, hf CLI and curl.
- Browser
- Download file 550 Bytes
-
https://huggingface.co/OwlMaster/FixRM/resolve/refs%2Fpr%2F1/onnx/quantize_config.json
- Command line
-
hf download hf://OwlMaster/FixRM@refs/pr/1/onnx/quantize_config.json
-
curl -L -o quantize_config.json https://huggingface.co/OwlMaster/FixRM/resolve/refs%2Fpr%2F1/onnx/quantize_config.json
550 Bytes
| { | |
| "per_channel": false, | |
| "reduce_range": false, | |
| "per_model_config": { | |
| "model": { | |
| "op_types": [ | |
| "Concat", | |
| "MaxPool", | |
| "Resize", | |
| "Conv", | |
| "Unsqueeze", | |
| "Cast", | |
| "Shape", | |
| "Relu", | |
| "Sigmoid", | |
| "Gather", | |
| "Constant", | |
| "Slice", | |
| "Add" | |
| ], | |
| "weight_type": "QUInt8" | |
| } | |
| } | |
| } |