Spaces:
Running
Running
| import numpy as np | |
| import torch | |
| import torch.nn.functional as F | |
| from torchvision.transforms.functional import normalize | |
| import gradio as gr | |
| from briarmbg import BriaRMBG | |
| import PIL | |
| from PIL import Image | |
| from typing import Tuple | |
| import requests | |
| from io import BytesIO | |
| net = BriaRMBG.from_pretrained("briaai/RMBG-1.4") | |
| device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |
| net.to(device) | |
| def resize_image(image): | |
| image = image.convert('RGB') | |
| model_input_size = (1024, 1024) | |
| image = image.resize(model_input_size, Image.BILINEAR) | |
| return image | |
| def get_url_image(url): | |
| headers = {'User-Agent': 'gradio-app'} | |
| response = requests.get(url, headers=headers) | |
| return BytesIO(response.content) | |
| def load_image(image_source): | |
| if isinstance(image_source, str): # Check if input is a URL | |
| print(f"Loading image from URL: {image_source}") | |
| image = Image.open(get_url_image(image_source)) | |
| else: | |
| print("Loading image from file upload") | |
| image = Image.fromarray(image_source) | |
| return image | |
| def process(image_source): | |
| try: | |
| # Load and prepare input | |
| orig_image = load_image(image_source) | |
| w, h = orig_im_size = orig_image.size | |
| image = resize_image(orig_image) | |
| im_np = np.array(image) | |
| im_tensor = torch.tensor(im_np, dtype=torch.float32).permute(2, 0, 1) | |
| im_tensor = torch.unsqueeze(im_tensor, 0) | |
| im_tensor = torch.divide(im_tensor, 255.0) | |
| im_tensor = normalize(im_tensor, [0.5, 0.5, 0.5], [1.0, 1.0, 1.0]) | |
| if torch.cuda.is_available(): | |
| im_tensor = im_tensor.cuda() | |
| # Inference | |
| result = net(im_tensor) | |
| # Post-process | |
| result = torch.squeeze(F.interpolate(result[0][0], size=(h, w), mode='bilinear'), 0) | |
| ma = torch.max(result) | |
| mi = torch.min(result) | |
| result = (result - mi) / (ma - mi) | |
| # Image to PIL | |
| im_array = (result * 255).cpu().data.numpy().astype(np.uint8) | |
| pil_im = Image.fromarray(np.squeeze(im_array)) | |
| # Paste the mask on the original image | |
| new_im = Image.new("RGBA", pil_im.size, (0, 0, 0, 0)) | |
| new_im.paste(orig_image, mask=pil_im) | |
| return new_im | |
| except Exception as e: | |
| print(f"Error during processing: {e}") | |
| return None | |
| title = "Background Removal" | |
| description = r"""Background removal model developed by <a href='https://BRIA.AI' target='_blank'><b>BRIA.AI</b></a>, trained on a carefully selected dataset and is available as an open-source model for non-commercial use.<br> | |
| For test upload your image and wait. Read more at model card <a href='https://huggingface.co/briaai/RMBG-1.4' target='_blank'><b>briaai/RMBG-1.4</b></a>.<br> | |
| """ | |
| examples = [['./input.jpg'],] | |
| demo = gr.Interface( | |
| fn=process, | |
| inputs=[ | |
| gr.Image(type="numpy", label="Upload Image"), | |
| gr.Textbox(label="Image URL") | |
| ], | |
| outputs="image", | |
| examples=examples, | |
| title=title, | |
| description=description | |
| ) | |
| if __name__ == "__main__": | |
| demo.launch(share=False) |