import numpy as np
import torch
import torch.nn.functional as F
import gradio as gr
from ormbg import ORMBG
from PIL import Image
model_path = "ormbg.pth"
net = ORMBG()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
net.to(device)
if torch.cuda.is_available():
net.load_state_dict(torch.load(model_path))
net = net.cuda()
else:
net.load_state_dict(torch.load(model_path, map_location="cpu"))
net.eval()
def resize_image(image):
image = image.convert("RGB")
model_input_size = (1024, 1024)
image = image.resize(model_input_size, Image.BILINEAR)
return image
def inference(image):
# prepare input
orig_image = Image.fromarray(image)
w, h = 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)
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
gr.Markdown("## Open Remove Background Model (ormbg)")
gr.HTML(
"""
This is a demo for Open Remove Background Model (ormbg) that using
Open Remove Background Model (ormbg) model as backbone.
"""
)
title = "Open Remove Background Model (ormbg)"
description = r"""
This model is a fully open-source background remover optimized for images with humans.
It is based on [Highly Accurate Dichotomous Image Segmentation research](https://github.com/xuebinqin/DIS).
The model was trained with the synthetic [Human Segmentation Dataset](https://huggingface.co/datasets/schirrmacher/humans).
This is the first iteration of the model, so there will be improvements!
If you identify cases were the model fails, upload your examples!
- Model card: find inference code, training information, tutorials
- Dataset: see training images, segmentation data, backgrounds
- Research: see current approach for improvements
"""
examples = ["./example1.png", "./example2.png", "./example3.png"]
demo = gr.Interface(
fn=inference,
inputs="image",
outputs="image",
examples=examples,
title=title,
description=description,
)
if __name__ == "__main__":
demo.launch(share=False)