|
--- |
|
library_name: transformers |
|
pipeline_tag: image-segmentation |
|
--- |
|
|
|
# How to use |
|
either load the model |
|
```python |
|
from transformers import AutoModelForImageSegmentation |
|
model = AutoModelForImageSegmentation.from_pretrained("briaai/RMBG-1.4",revision ="refs/pr/9",trust_remote_code=True) |
|
``` |
|
or load the pipeline |
|
```python |
|
from transformers import pipeline |
|
|
|
pipe = pipeline("image-segmentation", model="briaai/RMBG-1.4",revision ="refs/pr/9", trust_remote_code=True) |
|
|
|
numpy_mask = pipe("img_path") # outputs numpy mask |
|
|
|
pipe("image_path",out_name="myout.png") # applies mask and saves the extracted image as `myout.png` |
|
|
|
``` |
|
|
|
|
|
|
|
|
|
# parameters : |
|
for the pipeline you can use the following parameters : |
|
* `model_input_size` : default to [1024,1024] |
|
* `out_name` : if specified it will use the numpy mask to extract the image and save it using the `out_name` |
|
* `preprocess_image` : original method created by briaai |
|
* `postprocess_image` : original method created by briaai |
|
|
|
# disclamer |
|
I do not own, distribute or take credit for this model. |
|
|
|
All rights belong to [briaai](https://huggingface.co/briaai/) |
|
|
|
This repo is a temporary one to test out the custom architecture for [RMBG-1.4](https://huggingface.co/briaai/RMBG-1.4), please do refer to the original model. |
|
|
