File size: 2,381 Bytes
44b2a9b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
#!/usr/bin/env python3
"""
Simple usage example for ISNet Background Remover
Shows how to use the model with one-line loading
"""
from PIL import Image
from skimage import io
import torch
import torch.nn.functional as F
from transformers import AutoModelForImageSegmentation
from torchvision.transforms.functional import normalize
import numpy as np
def preprocess_image(im: np.ndarray, model_input_size: list) -> torch.Tensor:
"""Preprocess image for model input"""
if len(im.shape) < 3:
im = im[:, :, np.newaxis]
im_tensor = torch.tensor(im, dtype=torch.float32).permute(2,0,1)
im_tensor = F.interpolate(torch.unsqueeze(im_tensor,0), size=model_input_size, mode='bilinear')
image = torch.divide(im_tensor,255.0)
image = normalize(image,[0.5,0.5,0.5],[1.0,1.0,1.0])
return image
def postprocess_image(result: torch.Tensor, im_size: list)-> np.ndarray:
"""Postprocess model output to get mask"""
result = torch.squeeze(F.interpolate(result, size=im_size, mode='bilinear') ,0)
ma = torch.max(result)
mi = torch.min(result)
result = (result-mi)/(ma-mi)
im_array = (result*255).permute(1,2,0).cpu().data.numpy().astype(np.uint8)
im_array = np.squeeze(im_array)
return im_array
def main():
# One-line model loading with trust_remote_code=True
model = AutoModelForImageSegmentation.from_pretrained("mateenahmed/isnet-background-remover", trust_remote_code=True)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)
# Example image URL
image_path = "https://farm5.staticflickr.com/4007/4322154488_997e69e4cf_z.jpg"
orig_im = io.imread(image_path)
orig_im_size = orig_im.shape[0:2]
model_input_size = [1024, 1024]
# Preprocess image
image = preprocess_image(orig_im, model_input_size).to(device)
# Inference
result = model(image)
# Post process
result_image = postprocess_image(result, orig_im_size)
# Save result
pil_mask_im = Image.fromarray(result_image)
orig_image = Image.open(image_path)
no_bg_image = orig_image.copy()
no_bg_image.putalpha(pil_mask_im)
no_bg_image.save("output_no_bg.png")
print("✅ Background removed! Check output_no_bg.png")
if __name__ == "__main__":
main() |